
#import sys
#!{sys.executable} -m pip install pandas-profiling

#Libraries to help with reading data and manipulating data
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

# Libraries that support data visualization
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns

# Libraries to suppress warnings
import warnings 
warnings.filterwarnings("ignore")

sns.set()

# to split the data into train and test
from sklearn.model_selection import train_test_split

# to build logistic regression_model
from sklearn.linear_model import LogisticRegression

# to check model performance
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score

# to build linear regression_model using statsmodels
import statsmodels.api as sm

from sklearn.tree import DecisionTreeClassifier
from sklearn import tree

# Removes the limit for the number of displayed columns
pd.set_option("display.max_columns", None)
# Sets the limit for the number of displayed rows
pd.set_option("display.max_rows", 200)


# To build model for prediction
import statsmodels.stats.api as sms
from statsmodels.stats.outliers_influence import variance_inflation_factor
import statsmodels.api as sm
from statsmodels.tools.tools import add_constant
from sklearn.linear_model import LogisticRegression


# To get diferent metric scores
from sklearn.metrics import (
    f1_score,
    accuracy_score,
    recall_score,
    precision_score,
    confusion_matrix,
    roc_auc_score,
    plot_confusion_matrix,
    precision_recall_curve,
    roc_curve,
    make_scorer,
)

from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree
import sklearn.metrics as metrics

# To tune different models
from sklearn.model_selection import GridSearchCV

# Libraries to suppress warnings
import warnings 
warnings.filterwarnings("ignore")


#Load the dataset


data = pd.read_csv("StarHotelsGroup.csv")


#copying data to another data frame to avaoid changes in the original data
data_new = data.copy()


data_new.head() # display 5 rows from the dataframe


data_new.shape

(56926, 18)


# Selecting duplicate rows except first 
# occurrence based on all columns
duplicate = data_new[data_new.duplicated()]


duplicate


# Dropping all the duplicates in the dataframe.
df = data_new.drop_duplicates()
df


# Selecting duplicate rows except first 
# occurrence based on all columns
duplicate_new = df[df.duplicated()]


duplicate_new


df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 42576 entries, 0 to 56924
Data columns (total 18 columns):
 #   Column                                Non-Null Count  Dtype  
---  ------                                --------------  -----  
 0   no_of_adults                          42576 non-null  int64  
 1   no_of_children                        42576 non-null  int64  
 2   no_of_weekend_nights                  42576 non-null  int64  
 3   no_of_week_nights                     42576 non-null  int64  
 4   type_of_meal_plan                     42576 non-null  object 
 5   required_car_parking_space            42576 non-null  int64  
 6   room_type_reserved                    42576 non-null  object 
 7   lead_time                             42576 non-null  int64  
 8   arrival_year                          42576 non-null  int64  
 9   arrival_month                         42576 non-null  int64  
 10  arrival_date                          42576 non-null  int64  
 11  market_segment_type                   42576 non-null  object 
 12  repeated_guest                        42576 non-null  int64  
 13  no_of_previous_cancellations          42576 non-null  int64  
 14  no_of_previous_bookings_not_canceled  42576 non-null  int64  
 15  avg_price_per_room                    42576 non-null  float64
 16  no_of_special_requests                42576 non-null  int64  
 17  booking_status                        42576 non-null  object 
dtypes: float64(1), int64(13), object(4)
memory usage: 6.2+ MB


df.describe().T


df.describe(exclude='number').T


category = ['type_of_meal_plan', 'room_type_reserved', 'market_segment_type', 'booking_status']

for column in category:
    print(df[column].value_counts())
    print('_'*40)

Meal Plan 1     31863
Not Selected     8716
Meal Plan 2      1989
Meal Plan 3         8
Name: type_of_meal_plan, dtype: int64
________________________________________
Room_Type 1    29730
Room_Type 4     9369
Room_Type 6     1540
Room_Type 5      906
Room_Type 2      718
Room_Type 7      307
Room_Type 3        6
Name: room_type_reserved, dtype: int64
________________________________________
Online           34169
Offline           5777
Corporate         1939
Complementary      496
Aviation           195
Name: market_segment_type, dtype: int64
________________________________________
Not_Canceled    28089
Canceled        14487
Name: booking_status, dtype: int64
________________________________________


df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 42576 entries, 0 to 56924
Data columns (total 18 columns):
 #   Column                                Non-Null Count  Dtype  
---  ------                                --------------  -----  
 0   no_of_adults                          42576 non-null  int64  
 1   no_of_children                        42576 non-null  int64  
 2   no_of_weekend_nights                  42576 non-null  int64  
 3   no_of_week_nights                     42576 non-null  int64  
 4   type_of_meal_plan                     42576 non-null  object 
 5   required_car_parking_space            42576 non-null  int64  
 6   room_type_reserved                    42576 non-null  object 
 7   lead_time                             42576 non-null  int64  
 8   arrival_year                          42576 non-null  int64  
 9   arrival_month                         42576 non-null  int64  
 10  arrival_date                          42576 non-null  int64  
 11  market_segment_type                   42576 non-null  object 
 12  repeated_guest                        42576 non-null  int64  
 13  no_of_previous_cancellations          42576 non-null  int64  
 14  no_of_previous_bookings_not_canceled  42576 non-null  int64  
 15  avg_price_per_room                    42576 non-null  float64
 16  no_of_special_requests                42576 non-null  int64  
 17  booking_status                        42576 non-null  object 
dtypes: float64(1), int64(13), object(4)
memory usage: 6.2+ MB


print(df.type_of_meal_plan.unique())

['Meal Plan 1' 'Not Selected' 'Meal Plan 2' 'Meal Plan 3']


print(df.room_type_reserved.unique())

['Room_Type 1' 'Room_Type 4' 'Room_Type 6' 'Room_Type 5' 'Room_Type 2'
 'Room_Type 7' 'Room_Type 3']


print(df.market_segment_type.unique())

['Offline' 'Online' 'Corporate' 'Aviation' 'Complementary']


print(df.booking_status.unique())

['Not_Canceled' 'Canceled']


df.describe(include='all').T


 df.isna().sum()

no_of_adults                            0
no_of_children                          0
no_of_weekend_nights                    0
no_of_week_nights                       0
type_of_meal_plan                       0
required_car_parking_space              0
room_type_reserved                      0
lead_time                               0
arrival_year                            0
arrival_month                           0
arrival_date                            0
market_segment_type                     0
repeated_guest                          0
no_of_previous_cancellations            0
no_of_previous_bookings_not_canceled    0
avg_price_per_room                      0
no_of_special_requests                  0
booking_status                          0
dtype: int64


df.isnull().sum()

no_of_adults                            0
no_of_children                          0
no_of_weekend_nights                    0
no_of_week_nights                       0
type_of_meal_plan                       0
required_car_parking_space              0
room_type_reserved                      0
lead_time                               0
arrival_year                            0
arrival_month                           0
arrival_date                            0
market_segment_type                     0
repeated_guest                          0
no_of_previous_cancellations            0
no_of_previous_bookings_not_canceled    0
avg_price_per_room                      0
no_of_special_requests                  0
booking_status                          0
dtype: int64


['type_of_meal_plan', 'room_type_reserved', 'market_segment_type', 'booking_status']

['type_of_meal_plan',
 'room_type_reserved',
 'market_segment_type',
 'booking_status']


df.type_of_meal_plan = df.type_of_meal_plan.astype('category')
df.room_type_reserved = df.room_type_reserved.astype('category')
df.market_segment_type = df.market_segment_type.astype('category')
df.booking_status = df.booking_status.astype('category')


df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 42576 entries, 0 to 56924
Data columns (total 18 columns):
 #   Column                                Non-Null Count  Dtype   
---  ------                                --------------  -----   
 0   no_of_adults                          42576 non-null  int64   
 1   no_of_children                        42576 non-null  int64   
 2   no_of_weekend_nights                  42576 non-null  int64   
 3   no_of_week_nights                     42576 non-null  int64   
 4   type_of_meal_plan                     42576 non-null  category
 5   required_car_parking_space            42576 non-null  int64   
 6   room_type_reserved                    42576 non-null  category
 7   lead_time                             42576 non-null  int64   
 8   arrival_year                          42576 non-null  int64   
 9   arrival_month                         42576 non-null  int64   
 10  arrival_date                          42576 non-null  int64   
 11  market_segment_type                   42576 non-null  category
 12  repeated_guest                        42576 non-null  int64   
 13  no_of_previous_cancellations          42576 non-null  int64   
 14  no_of_previous_bookings_not_canceled  42576 non-null  int64   
 15  avg_price_per_room                    42576 non-null  float64 
 16  no_of_special_requests                42576 non-null  int64   
 17  booking_status                        42576 non-null  category
dtypes: category(4), float64(1), int64(13)
memory usage: 5.0 MB


sns.histplot(df.no_of_adults, kde=True);


sns.boxplot(df.no_of_adults,orient = "h");


sns.histplot(df.no_of_children, kde=True);


sns.boxplot(df.no_of_children,orient = "h");


sns.histplot(df.no_of_weekend_nights, kde=True);


sns.boxplot(df.no_of_weekend_nights,orient = "h");


sns.histplot(df.required_car_parking_space, kde=True);


sns.histplot(df.lead_time)

<AxesSubplot:xlabel='lead_time', ylabel='Count'>


sns.boxplot(df.lead_time,orient = "h");


sns.histplot(df.arrival_month)

<AxesSubplot:xlabel='arrival_month', ylabel='Count'>


sns.boxplot(df.arrival_month,orient = "h");


sns.histplot(df.repeated_guest)

<AxesSubplot:xlabel='repeated_guest', ylabel='Count'>


sns.histplot(df.no_of_previous_cancellations)

<AxesSubplot:xlabel='no_of_previous_cancellations', ylabel='Count'>


sns.histplot(df.no_of_previous_bookings_not_canceled)

<AxesSubplot:xlabel='no_of_previous_bookings_not_canceled', ylabel='Count'>


sns.histplot(df.no_of_special_requests)

<AxesSubplot:xlabel='no_of_special_requests', ylabel='Count'>


sns.histplot(df.type_of_meal_plan)

<AxesSubplot:xlabel='type_of_meal_plan', ylabel='Count'>


sns.countplot(df.room_type_reserved)

<AxesSubplot:xlabel='room_type_reserved', ylabel='count'>


sns.countplot(df.market_segment_type)

<AxesSubplot:xlabel='market_segment_type', ylabel='count'>


sns.countplot(df.booking_status)

<AxesSubplot:xlabel='booking_status', ylabel='count'>


df["booking_status"].replace({"Canceled": 1, "Not_Canceled": 0}, inplace=True)


column_list = df.select_dtypes(include=np.number).columns.tolist()
# dropping release_year as it is a temporal variable

plt.figure(figsize=(15, 7))
sns.heatmap(
    df[column_list].corr(), annot=True, vmin=-1, vmax=1, fmt=".2f", cmap="Spectral"
)
plt.show()


sns.pairplot(df);


sns.countplot(x="type_of_meal_plan", hue="room_type_reserved", data=df, palette='Set1',saturation=50 );


sns.countplot(x="type_of_meal_plan", hue="market_segment_type", data=df, palette='Set1',saturation=50 );


sns.countplot(x="type_of_meal_plan", hue="booking_status", data=df, palette='Set1',saturation=50 );


sns.countplot(x="room_type_reserved", hue="market_segment_type", data=df, palette='Set1',saturation=50 );


sns.countplot(x="market_segment_type", hue="booking_status", data=df, palette='Set1',saturation=50 );


sns.countplot(x="room_type_reserved", hue="booking_status", data=df, palette='Set1',saturation=50 );


fig = plt.figure(figsize= (10,5))
ax = sns.regplot(x ='no_of_adults', y = df['avg_price_per_room'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.lineplot(x ='no_of_children', y = df['booking_status'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.regplot(x ='no_of_weekend_nights', y = df['booking_status'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.regplot(x ='no_of_week_nights', y = df['booking_status'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='required_car_parking_space', y = df['booking_status'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.lineplot(x ='lead_time', y = df['booking_status'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='arrival_year', y = df['booking_status'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='arrival_month', y = df['booking_status'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.regplot(x ='no_of_previous_cancellations', y = df['booking_status'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.scatterplot(x ='no_of_previous_bookings_not_canceled', y = df['booking_status'], data = df)


booking_statusfig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='no_of_special_requests', y = df['booking_status'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='booking_status', y = df['avg_price_per_room'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='type_of_meal_plan', y = df['booking_status'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='market_segment_type', y = df['booking_status'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='room_type_reserved', y = df['booking_status'], data = df)


figure = plt.figure(figsize=(8,7))
sns.barplot(x="type_of_meal_plan", y="avg_price_per_room", data=df, hue='room_type_reserved', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.barplot(x="type_of_meal_plan", y="avg_price_per_room", data=df, hue='market_segment_type', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.barplot(x="type_of_meal_plan", y="avg_price_per_room", data=df, hue='booking_status', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.pointplot(x="room_type_reserved", y="avg_price_per_room", data=df, hue='market_segment_type', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.barplot(x="room_type_reserved", y="avg_price_per_room", data=df, hue='market_segment_type', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.pointplot(x="room_type_reserved", y="avg_price_per_room", data=df, hue='booking_status', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.barplot(x="room_type_reserved", y="avg_price_per_room", data=df, hue='booking_status', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.pointplot(x="market_segment_type", y="avg_price_per_room", data=df, hue='booking_status', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.barplot(x="market_segment_type", y="avg_price_per_room", data=df, hue='booking_status', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.pointplot(x="market_segment_type", y="no_of_previous_cancellations", data=df, hue='booking_status', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.pointplot(x="type_of_meal_plan", y="no_of_previous_bookings_not_canceled", data=df, hue='booking_status', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.barplot(x="type_of_meal_plan", y="no_of_previous_cancellations", data=df, hue='market_segment_type', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.barplot(x="type_of_meal_plan", y="no_of_special_requests", data=df, hue='room_type_reserved', palette='tab10' )
plt.show()


 ax = sns.violinplot(x =data.room_type_reserved, y = data['avg_price_per_room'])


 ax = sns.violinplot(x =data.type_of_meal_plan, y = data['avg_price_per_room'])


sns.histplot(df.arrival_month)

<AxesSubplot:xlabel='arrival_month', ylabel='Count'>


sns.boxplot(df.arrival_month,orient = "h");


sns.countplot(df.market_segment_type)

<AxesSubplot:xlabel='market_segment_type', ylabel='count'>


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='market_segment_type', y = df['avg_price_per_room'], data = df)


def labeled_barplot(data, feature, perc=False, n=None):

    total = len(data[feature])  # length of the column
    count = data[feature].nunique()
    if n is None:
        plt.figure(figsize=(count + 1, 5))
    else:
        plt.figure(figsize=(n + 1, 5))

    plt.xticks(rotation=90, fontsize=15)
    ax = sns.countplot(
        data=data,
        x=feature,
        palette="Paired",
        order=data[feature].value_counts().index[:n].sort_values(),
    )

    for p in ax.patches:
        if perc == True:
            label = "{:.1f}%".format(
                100 * p.get_height() / total
            ) 
        else:
            label = p.get_height()  # count of each level of the category

        x = p.get_x() + p.get_width() / 2  # width of the plot
        y = p.get_height()  # height of the plot

        ax.annotate(
            label,
            (x, y),
            ha="center",
            va="center",
            size=12,
            xytext=(0, 5),
            textcoords="offset points",
        )  

    plt.show()


labeled_barplot(df, "booking_status", perc=True)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='booking_status', y = df['repeated_guest'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='no_of_previous_cancellations', y = df['repeated_guest'], data = df)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='booking_status', y = df['no_of_special_requests'], data = df)


# let's create a copy of the data
df1 = df.copy()


np.random.seed(42)


df1.sample(n=10)#Return a random sample of 10 rows from the dataframe 'data'


df1.isnull().sum().sort_values(ascending = False) 
#Return the count of missing values column-wise and sort them in descending order

no_of_adults                            0
no_of_children                          0
no_of_special_requests                  0
avg_price_per_room                      0
no_of_previous_bookings_not_canceled    0
no_of_previous_cancellations            0
repeated_guest                          0
market_segment_type                     0
arrival_date                            0
arrival_month                           0
arrival_year                            0
lead_time                               0
room_type_reserved                      0
required_car_parking_space              0
type_of_meal_plan                       0
no_of_week_nights                       0
no_of_weekend_nights                    0
booking_status                          0
dtype: int64

df1


# Lets look at the statistical summary of the data
df1.describe(include="all").T


df1['type_of_meal_plan'].value_counts()

Meal Plan 1     31863
Not Selected     8716
Meal Plan 2      1989
Meal Plan 3         8
Name: type_of_meal_plan, dtype: int64


df1['room_type_reserved'].value_counts()

Room_Type 1    29730
Room_Type 4     9369
Room_Type 6     1540
Room_Type 5      906
Room_Type 2      718
Room_Type 7      307
Room_Type 3        6
Name: room_type_reserved, dtype: int64


df1['market_segment_type'].value_counts()

Online           34169
Offline           5777
Corporate         1939
Complementary      496
Aviation           195
Name: market_segment_type, dtype: int64


df1['booking_status'].value_counts()

0    28089
1    14487
Name: booking_status, dtype: int64


# outlier detection using boxplot
numeric_columns = df1.select_dtypes(include=np.number).columns.tolist()

 #let's plot the boxplots of all columns to check for outliers
plt.figure(figsize=(20, 30))

for i, variable in enumerate(numeric_columns):
    plt.subplot(5, 4, i + 1)
    plt.boxplot(df1[variable], whis=1.5)
    plt.tight_layout()
    plt.title(variable)

plt.show()


# let's check the statistical summary of the data once
df1.describe(include="all").T


data_new.head() # display 5 rows from the dataframe


df1.shape

(42576, 18)


sns.histplot(df1.no_of_adults, kde=True);


sns.boxplot(df1.no_of_adults,orient = "h");


sns.histplot(df1.no_of_children, kde=True);


sns.boxplot(df1.no_of_children,orient = "h");


sns.histplot(df1.no_of_weekend_nights, kde=True);


sns.boxplot(df1.no_of_weekend_nights,orient = "h");


sns.histplot(df1.required_car_parking_space, kde=True);


sns.histplot(df1.lead_time)

<AxesSubplot:xlabel='lead_time', ylabel='Count'>


sns.boxplot(df1.lead_time,orient = "h");


sns.histplot(df1.arrival_month)

<AxesSubplot:xlabel='arrival_month', ylabel='Count'>


sns.boxplot(df1.arrival_month,orient = "h");


sns.histplot(df1.repeated_guest)

<AxesSubplot:xlabel='repeated_guest', ylabel='Count'>


sns.histplot(df1.no_of_previous_cancellations)

<AxesSubplot:xlabel='no_of_previous_cancellations', ylabel='Count'>


sns.histplot(df1.no_of_previous_bookings_not_canceled)

<AxesSubplot:xlabel='no_of_previous_bookings_not_canceled', ylabel='Count'>


sns.histplot(df1.no_of_special_requests)

<AxesSubplot:xlabel='no_of_special_requests', ylabel='Count'>


sns.histplot(df1.type_of_meal_plan)

<AxesSubplot:xlabel='type_of_meal_plan', ylabel='Count'>


sns.countplot(df1.room_type_reserved)

<AxesSubplot:xlabel='room_type_reserved', ylabel='count'>


sns.countplot(df1.market_segment_type)

<AxesSubplot:xlabel='market_segment_type', ylabel='count'>


sns.countplot(df1.booking_status)

<AxesSubplot:xlabel='booking_status', ylabel='count'>


sns.countplot(x="type_of_meal_plan", hue="room_type_reserved", data=df1, palette='Set1',saturation=50 );


sns.countplot(x="type_of_meal_plan", hue="market_segment_type", data=df1, palette='Set1',saturation=50 );


sns.countplot(x="type_of_meal_plan", hue="booking_status", data=df1, palette='Set1',saturation=50 );


sns.countplot(x="room_type_reserved", hue="market_segment_type", data=df1, palette='Set1',saturation=50 );


sns.countplot(x="market_segment_type", hue="booking_status", data=df1, palette='Set1',saturation=50 );


sns.countplot(x="room_type_reserved", hue="booking_status", data=df1, palette='Set1',saturation=50 );


fig = plt.figure(figsize= (10,5))
ax = sns.regplot(x ='no_of_adults', y = df1['avg_price_per_room'], data = df1)


fig = plt.figure(figsize= (10,5))
ax = sns.lineplot(x ='no_of_children', y = df1['booking_status'], data = df1)


fig = plt.figure(figsize= (10,5))
ax = sns.regplot(x ='no_of_weekend_nights', y = df1['booking_status'], data = df1)


fig = plt.figure(figsize= (10,5))
ax = sns.regplot(x ='no_of_week_nights', y = df1['booking_status'], data = df1)


booking_statusfig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='required_car_parking_space', y = df1['booking_status'], data = df1)


fig = plt.figure(figsize= (10,5))
ax = sns.lineplot(x ='lead_time', y = df1['booking_status'], data = df1)


fig = plt.figure(figsize= (10,5))
ax = sns.regplot(x ='arrival_year', y = df1['booking_status'], data = df1)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='no_of_special_requests', y = df1['booking_status'], data = df1)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='booking_status', y = df1['avg_price_per_room'], data = df1)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='market_segment_type', y = df1['booking_status'], data = df1)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='room_type_reserved', y = df1['booking_status'], data = df1)


figure = plt.figure(figsize=(8,7))
sns.barplot(x="type_of_meal_plan", y="avg_price_per_room", data=df1, hue='booking_status', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.pointplot(x="room_type_reserved", y="avg_price_per_room", data=df1, hue='booking_status', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.barplot(x="room_type_reserved", y="avg_price_per_room", data=df1, hue='booking_status', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.pointplot(x="market_segment_type", y="avg_price_per_room", data=df1, hue='booking_status', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.barplot(x="market_segment_type", y="avg_price_per_room", data=df1, hue='booking_status', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.pointplot(x="market_segment_type", y="no_of_previous_cancellations", data=df1, hue='booking_status', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.pointplot(x="type_of_meal_plan", y="no_of_previous_bookings_not_canceled", data=df1, hue='booking_status', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.barplot(x="type_of_meal_plan", y="no_of_previous_cancellations", data=df1, hue='market_segment_type', palette='tab10' )
plt.show()


figure = plt.figure(figsize=(8,7))
sns.barplot(x="type_of_meal_plan", y="no_of_special_requests", data=df1, hue='room_type_reserved', palette='tab10' )
plt.show()


sns.histplot(df1.arrival_month)

<AxesSubplot:xlabel='arrival_month', ylabel='Count'>


sns.boxplot(df1.arrival_month,orient = "h");


sns.countplot(df1.market_segment_type)

<AxesSubplot:xlabel='market_segment_type', ylabel='count'>


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='market_segment_type', y = df1['avg_price_per_room'], data = df1)


def labeled_barplot(data, feature, perc=False, n=None):

    total = len(data[feature])  # length of the column
    count = data[feature].nunique()
    if n is None:
        plt.figure(figsize=(count + 1, 5))
    else:
        plt.figure(figsize=(n + 1, 5))

    plt.xticks(rotation=90, fontsize=15)
    ax = sns.countplot(
        data=data,
        x=feature,
        palette="Paired",
        order=data[feature].value_counts().index[:n].sort_values(),
    )

    for p in ax.patches:
        if perc == True:
            label = "{:.1f}%".format(
                100 * p.get_height() / total
            ) 
        else:
            label = p.get_height()  # count of each level of the category

        x = p.get_x() + p.get_width() / 2  # width of the plot
        y = p.get_height()  # height of the plot

        ax.annotate(
            label,
            (x, y),
            ha="center",
            va="center",
            size=12,
            xytext=(0, 5),
            textcoords="offset points",
        )  

    plt.show()


labeled_barplot(df1, "booking_status", perc=True)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='booking_status', y = df1['repeated_guest'], data = df1)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='no_of_previous_cancellations', y = df1['repeated_guest'], data = df1)


fig = plt.figure(figsize= (10,5))
ax = sns.barplot(x ='booking_status', y = df1['no_of_special_requests'], data = df1)


X = df1.drop(['booking_status'], axis = 1) 
y = df1['booking_status']


X.head()


y.head()

0    0
1    0
2    1
3    1
4    1
Name: booking_status, dtype: int64


X = pd.get_dummies(X, columns = X.select_dtypes(include = ["object","category"]).columns.tolist(), drop_first = True)


X.head()


y.head()

0    0
1    0
2    1
3    1
4    1
Name: booking_status, dtype: int64


# Splitting the data into test and train data

x_train, x_test, y_train, y_test = train_test_split(X,y, test_size = 0.3, random_state = 1)
x_train_stats = x_train.copy()
y_train_stats = y_train.copy()
x_train_sklearn = x_train.copy()
y_train_sklearn = y_train.copy()


from statsmodels.stats.outliers_influence import variance_inflation_factor

def checking_vif(predictors):
    vif = pd.DataFrame()
    vif["feature"] = predictors.columns
    vif["VIF"] = [variance_inflation_factor(predictors.values,i)
                 for i in range(len(predictors.columns))
    ]
    return vif


checking_vif(x_train_stats)


# defining a function to compute different metrics to check performance of a classification model built using statsmodels
def model_performance_statsmodel(
    model, predictors, target, threshold=0.5
):
    # checking which probabilities are greater than threshold
    pred_temp = model.predict(predictors) > threshold
    # rounding off the above values to get classes
    pred = np.round(pred_temp)

    accuracy_value = accuracy_score(target, pred)  # to compute Accuracy
    recall_value = recall_score(target, pred)  # to compute Recall
    precision_value = precision_score(target, pred)  # to compute Precision
    f1_value = f1_score(target, pred)  # to compute F1-score

    df_perf = pd.DataFrame(
        {"Accuracy": accuracy_value, "Recall": recall_value, "Precision": precision_value, "F1": f1_value,},
        index=[0],
    )

    return df_perf


# defining a function to plot the confusion_matrix of a classification model


def confusion_matrix_for_statsmodel(model, predictors, target, threshold=0.5):
    """ model: classifier
    predictors: independent variables
    target: dependent variable
    threshold: threshold for classifying the observation as class 1
    """
    y_pred = model.predict(predictors) > threshold
    cm = confusion_matrix(target, y_pred)
    labels = np.asarray(
        [
            ["{0:0.0f}".format(item) + "\n{0:.2%}".format(item / cm.flatten().sum())]
            for item in cm.flatten()
        ]
    ).reshape(2, 2)

    plt.figure(figsize=(6, 4))
    sns.heatmap(cm, annot=labels, fmt="")
    plt.ylabel("True label")
    plt.xlabel("Predicted label")


# There are different solvers available. The newton-cg solver is faster for higher-dimensional data.

lg = LogisticRegression(solver="newton-cg", random_state=1)
model = lg.fit(x_train_sklearn, y_train_sklearn)


# predict on training set
y_pred_train = lg.predict(x_train_sklearn)


print("Training set performance:")
print("Accuracy:", accuracy_score(y_train_sklearn, y_pred_train))
print("Precision:", precision_score(y_train_sklearn, y_pred_train))
print("Recall:", recall_score(y_train_sklearn, y_pred_train))
print("F1:", f1_score(y_train_sklearn, y_pred_train))

Training set performance:
Accuracy: 0.7927054323390262
Precision: 0.7317188422917897
Recall: 0.6132066132066132
F1: 0.6672411935796617


# predict on the test set
y_pred_test = lg.predict(x_test)


print("Test set performance:")
print("Accuracy:", accuracy_score(y_test, y_pred_test))
print("Precision:", precision_score(y_test, y_pred_test))
print("Recall:", recall_score(y_test, y_pred_test))
print("F1:", f1_score(y_test, y_pred_test))

Test set performance:
Accuracy: 0.7905738667501762
Precision: 0.7353507565337002
Recall: 0.6094391244870041
F1: 0.6665004363545692


X = df1.drop(["booking_status"], axis=1)
Y = df1["booking_status"]


X.head()


X = pd.get_dummies(X, drop_first=True)


X.head()


# adding constant
X = sm.add_constant(X)

# Splitting data in train and test set
X_train, X_test, y_train, y_test = train_test_split(
    X, Y, test_size=0.30, random_state=1
)


# fit the logistic regression model
logit = sm.Logit(y_train, X_train.astype(float))
lg = logit.fit(disp=False)

print(lg.summary())

                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                29803
Model:                          Logit   Df Residuals:                    29775
Method:                           MLE   Df Model:                           27
Date:                Fri, 17 Sep 2021   Pseudo R-squ.:                  0.3293
Time:                        22:47:37   Log-Likelihood:                -12799.
converged:                      False   LL-Null:                       -19083.
Covariance Type:            nonrobust   LLR p-value:                     0.000
========================================================================================================
                                           coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------------
const                                   91.4613     68.734      1.331      0.183     -43.256     226.178
no_of_adults                            -0.0320      0.035     -0.904      0.366      -0.102       0.037
no_of_children                           0.1129      0.048      2.375      0.018       0.020       0.206
no_of_weekend_nights                     0.0337      0.018      1.874      0.061      -0.002       0.069
no_of_week_nights                        0.0732      0.011      6.885      0.000       0.052       0.094
required_car_parking_space              -1.5124      0.116    -13.007      0.000      -1.740      -1.285
lead_time                                0.0168      0.000     62.116      0.000       0.016       0.017
arrival_year                            -0.0468      0.034     -1.373      0.170      -0.114       0.020
arrival_month                           -0.0416      0.007     -6.146      0.000      -0.055      -0.028
arrival_date                            -0.0029      0.002     -1.650      0.099      -0.006       0.001
repeated_guest                          -3.0309      0.594     -5.099      0.000      -4.196      -1.866
no_of_previous_cancellations             0.2225      0.096      2.307      0.021       0.033       0.412
no_of_previous_bookings_not_canceled    -0.0098      0.053     -0.186      0.852      -0.113       0.093
avg_price_per_room                       0.0168      0.001     25.746      0.000       0.015       0.018
no_of_special_requests                  -1.2915      0.024    -54.838      0.000      -1.338      -1.245
type_of_meal_plan_Meal Plan 2           -0.1580      0.080     -1.982      0.048      -0.314      -0.002
type_of_meal_plan_Meal Plan 3            2.3659   4.29e+04   5.51e-05      1.000   -8.41e+04    8.42e+04
type_of_meal_plan_Not Selected           0.3612      0.043      8.413      0.000       0.277       0.445
room_type_reserved_Room_Type 2          -0.1851      0.127     -1.454      0.146      -0.435       0.064
room_type_reserved_Room_Type 3           0.3624      1.334      0.272      0.786      -2.251       2.976
room_type_reserved_Room_Type 4          -0.1271      0.044     -2.861      0.004      -0.214      -0.040
room_type_reserved_Room_Type 5          -0.2723      0.112     -2.422      0.015      -0.493      -0.052
room_type_reserved_Room_Type 6          -0.5080      0.120     -4.250      0.000      -0.742      -0.274
room_type_reserved_Room_Type 7          -0.7297      0.201     -3.634      0.000      -1.123      -0.336
market_segment_type_Complementary      -20.6061   4771.099     -0.004      0.997   -9371.787    9330.575
market_segment_type_Corporate           -0.3716      0.274     -1.357      0.175      -0.908       0.165
market_segment_type_Offline             -1.9833      0.260     -7.616      0.000      -2.494      -1.473
market_segment_type_Online               0.2361      0.254      0.930      0.352      -0.262       0.734
========================================================================================================


print("Training performance:")
model_performance_statsmodel(lg, X_train, y_train)

Training performance:


vif_series = pd.Series(
    [variance_inflation_factor(X_train.values, i) for i in range(X_train.shape[1])],
    index=X_train.columns,
    dtype=float,
)
print("Series before feature selection: \n\n{}\n".format(vif_series))

Series before feature selection: 

const                                   1.859237e+07
no_of_adults                            1.449389e+00
no_of_children                          2.075427e+00
no_of_weekend_nights                    1.083180e+00
no_of_week_nights                       1.130019e+00
required_car_parking_space              1.035963e+00
lead_time                               1.331931e+00
arrival_year                            1.797321e+00
arrival_month                           1.547549e+00
arrival_date                            1.004898e+00
repeated_guest                          2.016007e+00
no_of_previous_cancellations            1.509257e+00
no_of_previous_bookings_not_canceled    1.846098e+00
avg_price_per_room                      2.625662e+00
no_of_special_requests                  1.111299e+00
type_of_meal_plan_Meal Plan 2           1.098579e+00
type_of_meal_plan_Meal Plan 3           1.027720e+00
type_of_meal_plan_Not Selected          1.332580e+00
room_type_reserved_Room_Type 2          1.095587e+00
room_type_reserved_Room_Type 3          1.001228e+00
room_type_reserved_Room_Type 4          1.425579e+00
room_type_reserved_Room_Type 5          1.116252e+00
room_type_reserved_Room_Type 6          2.103918e+00
room_type_reserved_Room_Type 7          1.167633e+00
market_segment_type_Complementary       3.942072e+00
market_segment_type_Corporate           1.073452e+01
market_segment_type_Offline             2.744181e+01
market_segment_type_Online              3.647704e+01
dtype: float64


print(lg.summary())

                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                29803
Model:                          Logit   Df Residuals:                    29775
Method:                           MLE   Df Model:                           27
Date:                Fri, 17 Sep 2021   Pseudo R-squ.:                  0.3293
Time:                        22:47:39   Log-Likelihood:                -12799.
converged:                      False   LL-Null:                       -19083.
Covariance Type:            nonrobust   LLR p-value:                     0.000
========================================================================================================
                                           coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------------
const                                   91.4613     68.734      1.331      0.183     -43.256     226.178
no_of_adults                            -0.0320      0.035     -0.904      0.366      -0.102       0.037
no_of_children                           0.1129      0.048      2.375      0.018       0.020       0.206
no_of_weekend_nights                     0.0337      0.018      1.874      0.061      -0.002       0.069
no_of_week_nights                        0.0732      0.011      6.885      0.000       0.052       0.094
required_car_parking_space              -1.5124      0.116    -13.007      0.000      -1.740      -1.285
lead_time                                0.0168      0.000     62.116      0.000       0.016       0.017
arrival_year                            -0.0468      0.034     -1.373      0.170      -0.114       0.020
arrival_month                           -0.0416      0.007     -6.146      0.000      -0.055      -0.028
arrival_date                            -0.0029      0.002     -1.650      0.099      -0.006       0.001
repeated_guest                          -3.0309      0.594     -5.099      0.000      -4.196      -1.866
no_of_previous_cancellations             0.2225      0.096      2.307      0.021       0.033       0.412
no_of_previous_bookings_not_canceled    -0.0098      0.053     -0.186      0.852      -0.113       0.093
avg_price_per_room                       0.0168      0.001     25.746      0.000       0.015       0.018
no_of_special_requests                  -1.2915      0.024    -54.838      0.000      -1.338      -1.245
type_of_meal_plan_Meal Plan 2           -0.1580      0.080     -1.982      0.048      -0.314      -0.002
type_of_meal_plan_Meal Plan 3            2.3659   4.29e+04   5.51e-05      1.000   -8.41e+04    8.42e+04
type_of_meal_plan_Not Selected           0.3612      0.043      8.413      0.000       0.277       0.445
room_type_reserved_Room_Type 2          -0.1851      0.127     -1.454      0.146      -0.435       0.064
room_type_reserved_Room_Type 3           0.3624      1.334      0.272      0.786      -2.251       2.976
room_type_reserved_Room_Type 4          -0.1271      0.044     -2.861      0.004      -0.214      -0.040
room_type_reserved_Room_Type 5          -0.2723      0.112     -2.422      0.015      -0.493      -0.052
room_type_reserved_Room_Type 6          -0.5080      0.120     -4.250      0.000      -0.742      -0.274
room_type_reserved_Room_Type 7          -0.7297      0.201     -3.634      0.000      -1.123      -0.336
market_segment_type_Complementary      -20.6061   4771.099     -0.004      0.997   -9371.787    9330.575
market_segment_type_Corporate           -0.3716      0.274     -1.357      0.175      -0.908       0.165
market_segment_type_Offline             -1.9833      0.260     -7.616      0.000      -2.494      -1.473
market_segment_type_Online               0.2361      0.254      0.930      0.352      -0.262       0.734
========================================================================================================


#Since, p-value for market_segment_type_Complementary >0.05

X_train1 = X_train.drop(
    ["market_segment_type_Complementary"], axis=1
)

logit1 = sm.Logit(y_train, X_train1.astype(float))
lg1 = logit1.fit()

print(lg1.summary())

Warning: Maximum number of iterations has been exceeded.
         Current function value: 0.429843
         Iterations: 35
                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                29803
Model:                          Logit   Df Residuals:                    29776
Method:                           MLE   Df Model:                           26
Date:                Fri, 17 Sep 2021   Pseudo R-squ.:                  0.3287
Time:                        22:47:40   Log-Likelihood:                -12811.
converged:                      False   LL-Null:                       -19083.
Covariance Type:            nonrobust   LLR p-value:                     0.000
========================================================================================================
                                           coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------------
const                                   94.0777     68.671      1.370      0.171     -40.515     228.671
no_of_adults                            -0.0382      0.035     -1.081      0.280      -0.107       0.031
no_of_children                           0.1097      0.048      2.309      0.021       0.017       0.203
no_of_weekend_nights                     0.0348      0.018      1.936      0.053      -0.000       0.070
no_of_week_nights                        0.0747      0.011      7.026      0.000       0.054       0.096
required_car_parking_space              -1.5122      0.116    -13.010      0.000      -1.740      -1.284
lead_time                                0.0168      0.000     62.150      0.000       0.016       0.017
arrival_year                            -0.0483      0.034     -1.419      0.156      -0.115       0.018
arrival_month                           -0.0425      0.007     -6.278      0.000      -0.056      -0.029
arrival_date                            -0.0029      0.002     -1.669      0.095      -0.006       0.001
repeated_guest                          -2.9906      0.596     -5.016      0.000      -4.159      -1.822
no_of_previous_cancellations             0.2198      0.096      2.280      0.023       0.031       0.409
no_of_previous_bookings_not_canceled    -0.0110      0.053     -0.206      0.836      -0.115       0.093
avg_price_per_room                       0.0170      0.001     26.230      0.000       0.016       0.018
no_of_special_requests                  -1.2918      0.024    -54.878      0.000      -1.338      -1.246
type_of_meal_plan_Meal Plan 2           -0.1694      0.080     -2.126      0.034      -0.326      -0.013
type_of_meal_plan_Meal Plan 3          -13.1988   4430.434     -0.003      0.998   -8696.689    8670.291
type_of_meal_plan_Not Selected           0.3641      0.043      8.483      0.000       0.280       0.448
room_type_reserved_Room_Type 2          -0.1828      0.127     -1.437      0.151      -0.432       0.067
room_type_reserved_Room_Type 3           0.2969      1.291      0.230      0.818      -2.234       2.828
room_type_reserved_Room_Type 4          -0.1269      0.044     -2.857      0.004      -0.214      -0.040
room_type_reserved_Room_Type 5          -0.2810      0.112     -2.502      0.012      -0.501      -0.061
room_type_reserved_Room_Type 6          -0.5183      0.119     -4.338      0.000      -0.752      -0.284
room_type_reserved_Room_Type 7          -0.7480      0.201     -3.727      0.000      -1.141      -0.355
market_segment_type_Corporate            0.1044      0.269      0.388      0.698      -0.424       0.632
market_segment_type_Offline             -1.5005      0.255     -5.884      0.000      -2.000      -1.001
market_segment_type_Online               0.7117      0.249      2.856      0.004       0.223       1.200
========================================================================================================


# running a loop to drop variables with high p-value

# initial list of columns
cols = X_train1.columns.tolist()

# setting an initial max p-value
max_p_value = 1

while len(cols) > 0:
    # defining the train set
    X_train_aux = X_train1[cols]

    # fitting the model
    model = sm.Logit(y_train, X_train_aux).fit(disp=False)

    # getting the p-values and the maximum p-value
    p_values = model.pvalues
    max_p_value = max(p_values)

    # name of the variable with maximum p-value
    feature_with_p_max = p_values.idxmax()

    if max_p_value > 0.05:
        cols.remove(feature_with_p_max)
    else:
        break

selected_features = cols
print(selected_features)

['no_of_children', 'no_of_week_nights', 'required_car_parking_space', 'lead_time', 'arrival_year', 'arrival_month', 'repeated_guest', 'no_of_previous_cancellations', 'avg_price_per_room', 'no_of_special_requests', 'type_of_meal_plan_Not Selected', 'room_type_reserved_Room_Type 4', 'room_type_reserved_Room_Type 5', 'room_type_reserved_Room_Type 6', 'room_type_reserved_Room_Type 7', 'market_segment_type_Offline', 'market_segment_type_Online']


X_train2 = X_train1[selected_features]


logit2 = sm.Logit(y_train, X_train2.astype(float))
lg2 = logit2.fit(disp=False)

print(lg2.summary())

                           Logit Regression Results                           
==============================================================================
Dep. Variable:         booking_status   No. Observations:                29803
Model:                          Logit   Df Residuals:                    29786
Method:                           MLE   Df Model:                           16
Date:                Fri, 17 Sep 2021   Pseudo R-squ.:                  0.3283
Time:                        22:47:43   Log-Likelihood:                -12818.
converged:                       True   LL-Null:                       -19083.
Covariance Type:            nonrobust   LLR p-value:                     0.000
==================================================================================================
                                     coef    std err          z      P>|z|      [0.025      0.975]
--------------------------------------------------------------------------------------------------
no_of_children                     0.1040      0.046      2.280      0.023       0.015       0.193
no_of_week_nights                  0.0781      0.010      7.531      0.000       0.058       0.098
required_car_parking_space        -1.5107      0.116    -13.008      0.000      -1.738      -1.283
lead_time                          0.0166      0.000     66.053      0.000       0.016       0.017
arrival_year                      -0.0017   5.83e-05    -28.439      0.000      -0.002      -0.002
arrival_month                     -0.0365      0.006     -6.511      0.000      -0.047      -0.025
repeated_guest                    -3.0469      0.552     -5.517      0.000      -4.129      -1.964
no_of_previous_cancellations       0.2178      0.095      2.298      0.022       0.032       0.403
avg_price_per_room                 0.0163      0.001     29.189      0.000       0.015       0.017
no_of_special_requests            -1.2929      0.024    -54.990      0.000      -1.339      -1.247
type_of_meal_plan_Not Selected     0.3544      0.041      8.582      0.000       0.273       0.435
room_type_reserved_Room_Type 4    -0.1252      0.043     -2.910      0.004      -0.210      -0.041
room_type_reserved_Room_Type 5    -0.2865      0.112     -2.558      0.011      -0.506      -0.067
room_type_reserved_Room_Type 6    -0.4636      0.116     -3.983      0.000      -0.692      -0.235
room_type_reserved_Room_Type 7    -0.6971      0.198     -3.518      0.000      -1.086      -0.309
market_segment_type_Offline       -1.6072      0.119    -13.562      0.000      -1.840      -1.375
market_segment_type_Online         0.6216      0.106      5.872      0.000       0.414       0.829
==================================================================================================


# converting coefficients to odds
odds = np.exp(lg2.params)

# finding the percentage change
perc_change_odds = (np.exp(lg2.params) - 1) * 100

# removing limit from number of columns to display
pd.set_option("display.max_columns", None)

# adding the odds to a dataframe
pd.DataFrame({"Odds": odds, "Change_odd%": perc_change_odds}, index=X_train2.columns).T


# creating confusion matrix
confusion_matrix_for_statsmodel(lg2, X_train2, y_train)


log_reg_model_train_perf = model_performance_statsmodel(
    lg2, X_train2, y_train
)

print("Training performance:")
log_reg_model_train_perf

Training performance:


logit_roc_auc_train = roc_auc_score(y_train, lg2.predict(X_train2))
fpr, tpr, thresholds = roc_curve(y_train, lg2.predict(X_train2))
plt.figure(figsize=(7, 5))
plt.plot(fpr, tpr, label="Logistic Regression (area = %0.2f)" % logit_roc_auc_train)
plt.plot([0, 1], [0, 1], "r--")
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel("False Positive Rate")
plt.ylabel("True Positive Rate")
plt.title("Receiver operating characteristic")
plt.legend(loc="lower right")
plt.show()


# Optimal threshold as per AUC-ROC curve
# The optimal cut off would be where tpr is high and fpr is low
fpr, tpr, thresholds = roc_curve(y_train, lg2.predict(X_train2))

optimal_idx = np.argmax(tpr - fpr)
optimal_threshold_auc_roc = thresholds[optimal_idx]
print(optimal_threshold_auc_roc)

0.3068474177339848


# creating confusion matrix
confusion_matrix_for_statsmodel(
    lg2, X_train2, y_train, threshold=optimal_threshold_auc_roc
)


# checking model performance for this model
log_reg_model_train_perf_threshold_auc_roc = model_performance_statsmodel(
    lg2, X_train2, y_train, threshold=optimal_threshold_auc_roc
)
print("Training performance:")
log_reg_model_train_perf_threshold_auc_roc

Training performance:


y_scores = lg2.predict(X_train2)
prec, rec, tre = precision_recall_curve(y_train, y_scores,)


def plot_prec_recall_vs_tresh(precisions, recalls, thresholds):
    plt.plot(thresholds, precisions[:-1], "b--", label="precision")
    plt.plot(thresholds, recalls[:-1], "g--", label="recall")
    plt.xlabel("Threshold")
    plt.legend(loc="upper left")
    plt.ylim([0, 1])


plt.figure(figsize=(10, 7))
plot_prec_recall_vs_tresh(prec, rec, tre)
plt.show()


# setting the threshold
optimal_threshold_curve = 0.40


# creating confusion matrix
confusion_matrix_for_statsmodel(lg2, X_train2, y_train, threshold=optimal_threshold_curve)


log_reg_model_train_perf_threshold_curve = model_performance_statsmodel(
    lg2, X_train2, y_train, threshold=optimal_threshold_curve
)
print("Training performance:")
log_reg_model_train_perf_threshold_curve

Training performance:


# training performance comparison

models_train_comp_df = pd.concat(
    [
        log_reg_model_train_perf.T,
        log_reg_model_train_perf_threshold_auc_roc.T,
        log_reg_model_train_perf_threshold_curve.T,
    ],
    axis=1,
)
models_train_comp_df.columns = [
    "Logistic Regression sklearn",
    "Logistic Regression-0.307 Threshold",
    "Logistic Regression-0.40 Threshold",
]

print("Training performance comparison:")
models_train_comp_df

Training performance comparison:


X_test2 = X_test[list(X_train2.columns)].astype(float)


# creating confusion matrix
confusion_matrix_for_statsmodel(lg2, X_test2, y_test)


log_reg_model_test_perf = model_performance_statsmodel(
    lg2, X_test2, y_test
)

print("Test performance:")
log_reg_model_test_perf

Test performance:


logit_roc_auc_train = roc_auc_score(y_test, lg2.predict(X_test2))
fpr, tpr, thresholds = roc_curve(y_test, lg2.predict(X_test2))
plt.figure(figsize=(7, 5))
plt.plot(fpr, tpr, label="Logistic Regression (area = %0.2f)" % logit_roc_auc_train)
plt.plot([0, 1], [0, 1], "r--")
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel("False Positive Rate")
plt.ylabel("True Positive Rate")
plt.title("Receiver operating characteristic")
plt.legend(loc="lower right")
plt.show()


# creating confusion matrix
confusion_matrix_for_statsmodel(lg2, X_test2, y_test, threshold=optimal_threshold_auc_roc)


# checking model performance for this model
log_reg_model_test_perf_threshold_auc_roc = model_performance_statsmodel(
    lg2, X_test2, y_test, threshold=optimal_threshold_auc_roc
)
print("Test performance:")
log_reg_model_test_perf_threshold_auc_roc

Test performance:


# creating confusion matrix
confusion_matrix_for_statsmodel(lg2, X_test2, y_test, threshold=optimal_threshold_curve)


log_reg_model_test_perf_threshold_curve = model_performance_statsmodel(
    lg2, X_test2, y_test, threshold=optimal_threshold_curve
)
print("Test performance:")
log_reg_model_test_perf_threshold_curve

Test performance:


# training performance comparison

models_train_comp_df = pd.concat(
    [
        log_reg_model_train_perf.T,
        log_reg_model_train_perf_threshold_auc_roc.T,
        log_reg_model_train_perf_threshold_curve.T,
    ],
    axis=1,
)
models_train_comp_df.columns = [
    "Logistic Regression sklearn",
    "Logistic Regression-0.306 Threshold",
    "Logistic Regression-0.40 Threshold",
]

print("Training performance comparison:")
models_train_comp_df

Training performance comparison:


# testing performance comparison

models_test_comp_df = pd.concat(
    [
        log_reg_model_test_perf.T,
        log_reg_model_test_perf_threshold_auc_roc.T,
        log_reg_model_test_perf_threshold_curve.T,
    ],
    axis=1,
)
models_test_comp_df.columns = [
    "Logistic Regression sklearn",
    "Logistic Regression-0.306 Threshold",
    "Logistic Regression-0.42 Threshold",
]

print("Test set performance comparison:")
models_test_comp_df

Test set performance comparison:


dTree = DecisionTreeClassifier(criterion = 'gini', random_state=1)
dTree.fit(X_train, y_train)

DecisionTreeClassifier(random_state=1)


print("Accuracy on training set : ",dTree.score(X_train, y_train))
print("Accuracy on test set : ",dTree.score(X_test, y_test))

Accuracy on training set :  0.9967117404288159
Accuracy on test set :  0.7893212244578408


#Checking number of positives
y.sum(axis = 0)

14487


## Function to create confusion matrix
def make_confusion_matrix_for_model(model,y_actual,labels=[1, 0]):
    y_predict = model.predict(X_test)
    cm=metrics.confusion_matrix( y_actual, y_predict, labels=[0, 1])
    df_cm = pd.DataFrame(cm, index = [i for i in ["Actual - No","Actual - Yes"]],
                  columns = [i for i in ['Predicted - No','Predicted - Yes']])
    group_counts = ["{0:0.0f}".format(value) for value in
                cm.flatten()]
    group_percentages = ["{0:.2%}".format(value) for value in
                         cm.flatten()/np.sum(cm)]
    labels = [f"{v1}\n{v2}" for v1, v2 in
              zip(group_counts,group_percentages)]
    labels = np.asarray(labels).reshape(2,2)
    plt.figure(figsize = (10,7))
    sns.heatmap(df_cm, annot=labels,fmt='')
    plt.ylabel('True label')
    plt.xlabel('Predicted label')


##  Function to calculate recall score
def get_recall_value(model):
    predict_train = model.predict(X_train)
    predict_test = model.predict(X_test)
    print("Recall on training set : ",metrics.recall_score(y_train,predict_train))
    print("Recall on test set : ",metrics.recall_score(y_test,predict_test))


##  Function to calculate recall score
def get_f1_value(model):
    predict_train = model.predict(X_train)
    predict_test = model.predict(X_test)
    print("f1 on training set : ",metrics.f1_score(y_train,predict_train))
    print("f1 on test set : ",metrics.f1_score(y_test,predict_test))


make_confusion_matrix_for_model(dTree,y_test)


# Accuracy on train and test
print("Accuracy value of training set : ",dTree.score(X_train, y_train))
print("Accuracy value of test set : ",dTree.score(X_test, y_test))

Accuracy value of training set :  0.9967117404288159
Accuracy value of test set :  0.7893212244578408


# Recall on train and test
get_recall_value(dTree)

Recall on training set :  0.9902979902979903
Recall on test set :  0.6981304149566804


# Recall on train and test
get_f1_value(dTree)

f1 on training set :  0.995125348189415
f1 on test set :  0.6947249007373795


feature_names = list(X.columns)
print(feature_names)

['const', 'no_of_adults', 'no_of_children', 'no_of_weekend_nights', 'no_of_week_nights', 'required_car_parking_space', 'lead_time', 'arrival_year', 'arrival_month', 'arrival_date', 'repeated_guest', 'no_of_previous_cancellations', 'no_of_previous_bookings_not_canceled', 'avg_price_per_room', 'no_of_special_requests', 'type_of_meal_plan_Meal Plan 2', 'type_of_meal_plan_Meal Plan 3', 'type_of_meal_plan_Not Selected', 'room_type_reserved_Room_Type 2', 'room_type_reserved_Room_Type 3', 'room_type_reserved_Room_Type 4', 'room_type_reserved_Room_Type 5', 'room_type_reserved_Room_Type 6', 'room_type_reserved_Room_Type 7', 'market_segment_type_Complementary', 'market_segment_type_Corporate', 'market_segment_type_Offline', 'market_segment_type_Online']


#plt.figure(figsize=(20,30))
#tree.plot_tree(dTree,feature_names=feature_names,filled=True,fontsize=9,node_ids=True,class_names=True)
#plt.show()


# Text report showing the rules of a decision tree -

print(tree.export_text(dTree,feature_names=feature_names,show_weights=True))

|--- lead_time <= 150.50
|   |--- no_of_special_requests <= 0.50
|   |   |--- market_segment_type_Online <= 0.50
|   |   |   |--- lead_time <= 91.50
|   |   |   |   |--- avg_price_per_room <= 209.28
|   |   |   |   |   |--- no_of_weekend_nights <= 3.50
|   |   |   |   |   |   |--- avg_price_per_room <= 75.54
|   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |--- lead_time <= 17.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 6.50
|   |   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 7
|   |   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |   |--- arrival_month >  6.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_children <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 8
|   |   |   |   |   |   |   |   |   |   |--- no_of_children >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |--- lead_time >  17.50
|   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 67.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 11
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  67.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [17.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 15.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 8
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  15.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 14
|   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |--- repeated_guest <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 12
|   |   |   |   |   |   |   |   |   |   |--- repeated_guest >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [46.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [87.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 65.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [249.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- lead_time >  65.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 66.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  66.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [32.00, 0.00] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  75.54
|   |   |   |   |   |   |   |--- avg_price_per_room <= 75.62
|   |   |   |   |   |   |   |   |--- arrival_year <= 2018.00
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |   |--- arrival_year >  2018.00
|   |   |   |   |   |   |   |   |   |--- lead_time <= 66.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- lead_time >  66.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |--- avg_price_per_room >  75.62
|   |   |   |   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 44.50
|   |   |   |   |   |   |   |   |   |   |--- repeated_guest <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 15
|   |   |   |   |   |   |   |   |   |   |--- repeated_guest >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [116.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- lead_time >  44.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 70.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  70.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [464.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 57.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 17
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  57.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 12
|   |   |   |   |   |--- no_of_weekend_nights >  3.50
|   |   |   |   |   |   |--- arrival_month <= 4.50
|   |   |   |   |   |   |   |--- arrival_month <= 3.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |--- arrival_month >  3.50
|   |   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_month >  4.50
|   |   |   |   |   |   |   |--- market_segment_type_Complementary <= 0.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 6.00] class: 1
|   |   |   |   |   |   |   |--- market_segment_type_Complementary >  0.50
|   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |--- avg_price_per_room >  209.28
|   |   |   |   |   |--- weights: [0.00, 6.00] class: 1
|   |   |   |--- lead_time >  91.50
|   |   |   |   |--- avg_price_per_room <= 91.22
|   |   |   |   |   |--- no_of_week_nights <= 8.50
|   |   |   |   |   |   |--- lead_time <= 144.50
|   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [20.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 28.00
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 62.38
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 3.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  62.38
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 9
|   |   |   |   |   |   |   |   |   |--- arrival_date >  28.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [5.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 62.88
|   |   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  62.88
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 75.33
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 11
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  75.33
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 10
|   |   |   |   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |--- lead_time >  144.50
|   |   |   |   |   |   |   |--- weights: [34.00, 0.00] class: 0
|   |   |   |   |   |--- no_of_week_nights >  8.50
|   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |--- avg_price_per_room >  91.22
|   |   |   |   |   |--- avg_price_per_room <= 96.61
|   |   |   |   |   |   |--- arrival_date <= 6.50
|   |   |   |   |   |   |   |--- no_of_week_nights <= 4.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 9.00] class: 1
|   |   |   |   |   |   |   |--- no_of_week_nights >  4.50
|   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_date >  6.50
|   |   |   |   |   |   |   |--- lead_time <= 145.50
|   |   |   |   |   |   |   |   |--- lead_time <= 110.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- lead_time >  110.50
|   |   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 141.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  141.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [6.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- lead_time >  145.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |--- avg_price_per_room >  96.61
|   |   |   |   |   |   |--- avg_price_per_room <= 184.25
|   |   |   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |   |   |--- lead_time <= 93.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |   |--- lead_time >  93.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 130.25
|   |   |   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 11
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  130.25
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [12.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 116.19
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Corporate <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 4.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  4.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [40.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Corporate >  0.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 114.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  114.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  116.19
|   |   |   |   |   |   |   |   |   |--- lead_time <= 108.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [8.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- lead_time >  108.50
|   |   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [3.00, 0.00] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  184.25
|   |   |   |   |   |   |   |--- weights: [0.00, 3.00] class: 1
|   |   |--- market_segment_type_Online >  0.50
|   |   |   |--- lead_time <= 9.50
|   |   |   |   |--- avg_price_per_room <= 202.67
|   |   |   |   |   |--- lead_time <= 2.50
|   |   |   |   |   |   |--- no_of_week_nights <= 8.50
|   |   |   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |   |   |--- weights: [100.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 77.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  77.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 12
|   |   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 5.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 12
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  5.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 7
|   |   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [96.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 >  0.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [11.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |--- no_of_week_nights >  8.50
|   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |--- lead_time >  2.50
|   |   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |   |--- weights: [79.00, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 1.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 82.97
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 70.24
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  70.24
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 7
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  82.97
|   |   |   |   |   |   |   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 19
|   |   |   |   |   |   |   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [13.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  1.50
|   |   |   |   |   |   |   |   |   |--- arrival_year <= 2018.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 8
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |--- arrival_year >  2018.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |--- no_of_week_nights <= 4.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [32.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [66.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- no_of_week_nights >  4.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 3.00] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.00, 0.00] class: 0
|   |   |   |   |--- avg_price_per_room >  202.67
|   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |--- weights: [0.00, 50.00] class: 1
|   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |--- lead_time >  9.50
|   |   |   |   |--- avg_price_per_room <= 194.83
|   |   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |   |--- lead_time <= 25.50
|   |   |   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |   |   |--- lead_time <= 24.50
|   |   |   |   |   |   |   |   |   |--- weights: [107.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- lead_time >  24.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 123.75
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  123.75
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_year <= 2018.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 16
|   |   |   |   |   |   |   |   |   |   |--- arrival_year >  2018.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 17
|   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 24.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [98.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- lead_time >  24.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 100.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [4.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  100.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |--- lead_time >  25.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 74.62
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 24.85
|   |   |   |   |   |   |   |   |   |--- weights: [29.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  24.85
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 5.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 67.31
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 13
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  67.31
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 11
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  5.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 26.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  26.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |--- avg_price_per_room >  74.62
|   |   |   |   |   |   |   |   |--- arrival_year <= 2018.50
|   |   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 68.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  68.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 14
|   |   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 111.69
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 22
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  111.69
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 25
|   |   |   |   |   |   |   |   |--- arrival_year >  2018.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 5.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 37.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 15
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  37.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 28
|   |   |   |   |   |   |   |   |   |--- arrival_month >  5.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 111.80
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 11
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  111.80
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 19
|   |   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |   |--- weights: [93.00, 0.00] class: 0
|   |   |   |   |--- avg_price_per_room >  194.83
|   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |--- avg_price_per_room <= 200.35
|   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 4.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |--- arrival_date >  4.50
|   |   |   |   |   |   |   |   |   |--- weights: [4.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 7 <= 0.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_date >  1.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 143.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 7
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  143.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 7 >  0.50
|   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  200.35
|   |   |   |   |   |   |   |--- weights: [0.00, 263.00] class: 1
|   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |--- type_of_meal_plan_Meal Plan 2 <= 0.50
|   |   |   |   |   |   |   |--- weights: [5.00, 0.00] class: 0
|   |   |   |   |   |   |--- type_of_meal_plan_Meal Plan 2 >  0.50
|   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |--- no_of_special_requests >  0.50
|   |   |--- no_of_special_requests <= 1.50
|   |   |   |--- lead_time <= 7.50
|   |   |   |   |--- lead_time <= 4.50
|   |   |   |   |   |--- no_of_week_nights <= 11.00
|   |   |   |   |   |   |--- avg_price_per_room <= 125.58
|   |   |   |   |   |   |   |--- no_of_children <= 1.50
|   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 5.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [304.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_month >  5.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 86.72
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [135.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  86.72
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 8
|   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 81.40
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  81.40
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |--- arrival_date >  1.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 2.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 10
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  2.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 7
|   |   |   |   |   |   |   |--- no_of_children >  1.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 11.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |--- arrival_date >  11.50
|   |   |   |   |   |   |   |   |   |--- weights: [3.00, 0.00] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  125.58
|   |   |   |   |   |   |   |--- lead_time <= 0.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 181.17
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 4.50
|   |   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_month >  4.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 5.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  5.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  181.17
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 12.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [6.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_date >  12.50
|   |   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |--- lead_time >  0.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 126.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  126.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 4.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 13.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  13.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 10
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  4.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 3.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  3.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |--- no_of_week_nights >  11.00
|   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |--- lead_time >  4.50
|   |   |   |   |   |--- avg_price_per_room <= 108.99
|   |   |   |   |   |   |--- no_of_week_nights <= 12.50
|   |   |   |   |   |   |   |--- no_of_adults <= 0.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- no_of_adults >  0.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 77.88
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 2.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 6.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [17.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  6.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- arrival_month >  2.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [77.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  77.88
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 78.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  78.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 98.05
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 9
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  98.05
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [48.00, 0.00] class: 0
|   |   |   |   |   |   |--- no_of_week_nights >  12.50
|   |   |   |   |   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |--- avg_price_per_room >  108.99
|   |   |   |   |   |   |--- avg_price_per_room <= 109.25
|   |   |   |   |   |   |   |--- arrival_date <= 6.00
|   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |--- arrival_date >  6.00
|   |   |   |   |   |   |   |   |--- arrival_date <= 27.00
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 8.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_date >  8.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [4.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  27.00
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |--- avg_price_per_room >  109.25
|   |   |   |   |   |   |   |--- no_of_week_nights <= 7.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 138.79
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 5.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [13.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  5.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  138.79
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 165.88
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 3.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  3.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 8
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  165.88
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |--- no_of_week_nights >  7.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |--- lead_time >  7.50
|   |   |   |   |--- avg_price_per_room <= 121.78
|   |   |   |   |   |--- market_segment_type_Online <= 0.50
|   |   |   |   |   |   |--- lead_time <= 91.50
|   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 109.75
|   |   |   |   |   |   |   |   |   |--- weights: [434.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  109.75
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Corporate <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [30.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Corporate >  0.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 25.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [3.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  25.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 99.00
|   |   |   |   |   |   |   |   |   |--- weights: [18.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  99.00
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Corporate <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- market_segment_type_Corporate >  0.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 14.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  14.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 1.00] class: 0
|   |   |   |   |   |   |--- lead_time >  91.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 120.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 13.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 5.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 92.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  92.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [27.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_date >  5.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 9.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  9.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |--- arrival_date >  13.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_children <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- no_of_children >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 135.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [52.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  135.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |--- avg_price_per_room >  120.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |--- market_segment_type_Online >  0.50
|   |   |   |   |   |   |--- lead_time <= 68.50
|   |   |   |   |   |   |   |--- no_of_weekend_nights <= 2.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |   |   |   |--- weights: [241.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 21
|   |   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 23
|   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [195.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- no_of_weekend_nights >  2.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 10.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_date >  10.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 46.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [7.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  46.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 53.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 16.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  53.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |--- lead_time >  68.50
|   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 63.45
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  63.45
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 123.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  123.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 87.38
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 3.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  3.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 11
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  87.38
|   |   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Meal Plan 2 <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Meal Plan 2 >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 71.19
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 3.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 55.82
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  55.82
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |--- arrival_month >  3.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [42.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  71.19
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 3.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 14.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 10
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  14.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 18
|   |   |   |   |   |   |   |   |   |--- arrival_month >  3.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 8.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 16
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  8.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 14
|   |   |   |   |--- avg_price_per_room >  121.78
|   |   |   |   |   |--- required_car_parking_space <= 0.50
|   |   |   |   |   |   |--- avg_price_per_room <= 192.17
|   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |--- lead_time <= 27.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 149.67
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 4.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 14
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  4.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  149.67
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 17
|   |   |   |   |   |   |   |   |--- lead_time >  27.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 7.50
|   |   |   |   |   |   |   |   |   |   |--- market_segment_type_Offline <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 26
|   |   |   |   |   |   |   |   |   |   |--- market_segment_type_Offline >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  7.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 6.00] class: 1
|   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |--- arrival_year <= 2018.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 27.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 10.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 14
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  10.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [9.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- lead_time >  27.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 158.85
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 15
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  158.85
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |--- arrival_year >  2018.50
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 23.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 15
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  23.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 13
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  1.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 58.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 15
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  58.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 7
|   |   |   |   |   |   |--- avg_price_per_room >  192.17
|   |   |   |   |   |   |   |--- lead_time <= 87.00
|   |   |   |   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 21.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 311.40
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 8
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  311.40
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- lead_time >  21.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 23.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 9
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  23.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 29.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 25.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 9
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  25.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- arrival_date >  29.50
|   |   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 5 <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [6.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 5 >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |--- lead_time >  87.00
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 200.40
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 198.49
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 7
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  198.49
|   |   |   |   |   |   |   |   |   |   |--- weights: [4.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  200.40
|   |   |   |   |   |   |   |   |   |--- lead_time <= 92.00
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 20.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  20.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- lead_time >  92.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 25.00] class: 1
|   |   |   |   |   |--- required_car_parking_space >  0.50
|   |   |   |   |   |   |--- weights: [134.00, 0.00] class: 0
|   |   |--- no_of_special_requests >  1.50
|   |   |   |--- lead_time <= 90.50
|   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |--- lead_time <= 89.50
|   |   |   |   |   |   |--- weights: [2946.00, 0.00] class: 0
|   |   |   |   |   |--- lead_time >  89.50
|   |   |   |   |   |   |--- no_of_children <= 0.50
|   |   |   |   |   |   |   |--- weights: [13.00, 0.00] class: 0
|   |   |   |   |   |   |--- no_of_children >  0.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 121.50
|   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- avg_price_per_room >  121.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |--- no_of_week_nights <= 9.50
|   |   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |   |--- lead_time <= 6.50
|   |   |   |   |   |   |   |   |--- no_of_children <= 0.50
|   |   |   |   |   |   |   |   |   |--- weights: [50.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- no_of_children >  0.50
|   |   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_children <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- no_of_children >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [5.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- lead_time >  6.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 30.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [34.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 16
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [28.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  30.50
|   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 19.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  19.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.00] class: 1
|   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [3.00, 0.00] class: 0
|   |   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |   |--- weights: [108.00, 0.00] class: 0
|   |   |   |   |   |--- no_of_week_nights >  9.50
|   |   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |   |--- lead_time <= 3.00
|   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- lead_time >  3.00
|   |   |   |   |   |   |   |   |--- weights: [0.00, 5.00] class: 1
|   |   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |--- lead_time >  90.50
|   |   |   |   |--- avg_price_per_room <= 200.15
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- arrival_month <= 4.50
|   |   |   |   |   |   |   |--- arrival_year <= 2018.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 103.44
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 2.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_date >  2.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [24.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  103.44
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 151.65
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 3.00] class: 1
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  151.65
|   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- arrival_year >  2018.50
|   |   |   |   |   |   |   |   |--- no_of_week_nights <= 5.50
|   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 25.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  25.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 73.04
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  73.04
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 17
|   |   |   |   |   |   |   |   |--- no_of_week_nights >  5.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.00] class: 1
|   |   |   |   |   |   |--- arrival_month >  4.50
|   |   |   |   |   |   |   |--- arrival_month <= 10.50
|   |   |   |   |   |   |   |   |--- arrival_year <= 2017.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 2.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  2.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 21.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  21.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |   |--- arrival_year >  2017.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 9.00
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 10
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 13
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  9.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |--- arrival_month >  10.50
|   |   |   |   |   |   |   |   |--- no_of_week_nights <= 0.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 3.00] class: 1
|   |   |   |   |   |   |   |   |--- no_of_week_nights >  0.50
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 138.40
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 99.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  99.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 9
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  138.40
|   |   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 6 <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [11.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 6 >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [172.00, 0.00] class: 0
|   |   |   |   |--- avg_price_per_room >  200.15
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- weights: [0.00, 25.00] class: 1
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [5.00, 0.00] class: 0
|--- lead_time >  150.50
|   |--- avg_price_per_room <= 100.04
|   |   |--- market_segment_type_Online <= 0.50
|   |   |   |--- lead_time <= 274.00
|   |   |   |   |--- avg_price_per_room <= 89.55
|   |   |   |   |   |--- no_of_week_nights <= 9.50
|   |   |   |   |   |   |--- avg_price_per_room <= 27.07
|   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |--- avg_price_per_room >  27.07
|   |   |   |   |   |   |   |--- no_of_previous_cancellations <= 8.00
|   |   |   |   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 24.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 5.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  5.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 14
|   |   |   |   |   |   |   |   |   |--- arrival_date >  24.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_special_requests <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 6
|   |   |   |   |   |   |   |   |   |   |--- no_of_special_requests >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 205.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- lead_time >  205.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- no_of_previous_cancellations >  8.00
|   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |--- no_of_week_nights >  9.50
|   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |--- avg_price_per_room >  89.55
|   |   |   |   |   |--- lead_time <= 223.00
|   |   |   |   |   |   |--- arrival_month <= 6.50
|   |   |   |   |   |   |   |--- no_of_special_requests <= 0.50
|   |   |   |   |   |   |   |   |--- lead_time <= 183.50
|   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 5.00] class: 1
|   |   |   |   |   |   |   |   |   |--- room_type_reserved_Room_Type 4 >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- lead_time >  183.50
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_year <= 2018.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 3.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- arrival_year >  2018.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [5.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- no_of_special_requests >  0.50
|   |   |   |   |   |   |   |   |--- weights: [8.00, 0.00] class: 0
|   |   |   |   |   |   |--- arrival_month >  6.50
|   |   |   |   |   |   |   |--- arrival_date <= 30.50
|   |   |   |   |   |   |   |   |--- lead_time <= 155.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 154.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- lead_time >  154.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |--- lead_time >  155.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 195.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [26.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- lead_time >  195.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 201.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  201.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [10.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- arrival_date >  30.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |--- lead_time >  223.00
|   |   |   |   |   |   |--- avg_price_per_room <= 94.00
|   |   |   |   |   |   |   |--- avg_price_per_room <= 90.77
|   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 243.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- lead_time >  243.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.00] class: 1
|   |   |   |   |   |   |   |--- avg_price_per_room >  90.77
|   |   |   |   |   |   |   |   |--- weights: [4.00, 0.00] class: 0
|   |   |   |   |   |   |--- avg_price_per_room >  94.00
|   |   |   |   |   |   |   |--- no_of_special_requests <= 1.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 8.00] class: 1
|   |   |   |   |   |   |   |--- no_of_special_requests >  1.50
|   |   |   |   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |--- lead_time >  274.00
|   |   |   |   |--- lead_time <= 389.50
|   |   |   |   |   |--- avg_price_per_room <= 84.38
|   |   |   |   |   |   |--- lead_time <= 277.50
|   |   |   |   |   |   |   |--- weights: [0.00, 3.00] class: 1
|   |   |   |   |   |   |--- lead_time >  277.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 69.44
|   |   |   |   |   |   |   |   |--- arrival_date <= 24.00
|   |   |   |   |   |   |   |   |   |--- weights: [13.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  24.00
|   |   |   |   |   |   |   |   |   |--- lead_time <= 306.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- lead_time >  306.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |--- avg_price_per_room >  69.44
|   |   |   |   |   |   |   |   |--- lead_time <= 297.00
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 74.25
|   |   |   |   |   |   |   |   |   |   |--- no_of_special_requests <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 1.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- no_of_special_requests >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  74.25
|   |   |   |   |   |   |   |   |   |   |--- weights: [8.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- lead_time >  297.00
|   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 5.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 7
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  5.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |--- avg_price_per_room >  84.38
|   |   |   |   |   |   |--- lead_time <= 319.50
|   |   |   |   |   |   |   |--- type_of_meal_plan_Meal Plan 2 <= 0.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 14.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 4
|   |   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |   |--- arrival_date >  14.50
|   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 11.00] class: 1
|   |   |   |   |   |   |   |--- type_of_meal_plan_Meal Plan 2 >  0.50
|   |   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |   |--- lead_time >  319.50
|   |   |   |   |   |   |   |--- lead_time <= 345.50
|   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |   |--- no_of_special_requests <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [5.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- no_of_special_requests >  0.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [3.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- lead_time >  345.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 7.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  7.50
|   |   |   |   |   |   |   |   |   |--- no_of_special_requests <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_month <= 9.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 1.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- arrival_month >  9.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |--- no_of_special_requests >  0.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 1.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 1.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  1.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |--- lead_time >  389.50
|   |   |   |   |   |--- type_of_meal_plan_Meal Plan 2 <= 0.50
|   |   |   |   |   |   |--- weights: [0.00, 22.00] class: 1
|   |   |   |   |   |--- type_of_meal_plan_Meal Plan 2 >  0.50
|   |   |   |   |   |   |--- lead_time <= 414.00
|   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |   |--- lead_time >  414.00
|   |   |   |   |   |   |   |--- avg_price_per_room <= 22.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |--- avg_price_per_room >  22.50
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 59.25
|   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  59.25
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 1.00] class: 0
|   |   |--- market_segment_type_Online >  0.50
|   |   |   |--- no_of_special_requests <= 0.50
|   |   |   |   |--- avg_price_per_room <= 1.50
|   |   |   |   |   |--- lead_time <= 285.50
|   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |--- weights: [10.00, 0.00] class: 0
|   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |--- arrival_year <= 2018.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |--- arrival_year >  2018.50
|   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |--- lead_time >  285.50
|   |   |   |   |   |   |--- weights: [0.00, 5.00] class: 1
|   |   |   |   |--- avg_price_per_room >  1.50
|   |   |   |   |   |--- no_of_adults <= 2.50
|   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |--- weights: [0.00, 558.00] class: 1
|   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |--- no_of_week_nights <= 1.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 3.50
|   |   |   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  3.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 214.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- lead_time >  214.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 6.00] class: 1
|   |   |   |   |   |   |   |--- no_of_week_nights >  1.50
|   |   |   |   |   |   |   |   |--- lead_time <= 223.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 212.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 10.00] class: 1
|   |   |   |   |   |   |   |   |   |--- lead_time >  212.50
|   |   |   |   |   |   |   |   |   |   |--- arrival_date <= 18.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- arrival_date >  18.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- lead_time >  223.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 39.00] class: 1
|   |   |   |   |   |--- no_of_adults >  2.50
|   |   |   |   |   |   |--- lead_time <= 164.50
|   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |--- lead_time >  164.50
|   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |--- no_of_special_requests >  0.50
|   |   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |   |--- lead_time <= 180.50
|   |   |   |   |   |   |--- arrival_month <= 2.50
|   |   |   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |   |   |--- arrival_date <= 18.50
|   |   |   |   |   |   |   |   |   |--- weights: [3.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_date >  18.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 3.00] class: 1
|   |   |   |   |   |   |--- arrival_month >  2.50
|   |   |   |   |   |   |   |--- arrival_date <= 22.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 3.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 17.00
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 3.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  3.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_date >  17.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [2.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- arrival_month >  3.50
|   |   |   |   |   |   |   |   |   |--- arrival_date <= 5.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 178.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  178.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_date >  5.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |--- arrival_date >  22.50
|   |   |   |   |   |   |   |   |--- arrival_month <= 10.50
|   |   |   |   |   |   |   |   |   |--- no_of_adults <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |   |   |--- no_of_adults >  1.50
|   |   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected <= 0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- type_of_meal_plan_Not Selected >  0.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |--- arrival_month >  10.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |--- lead_time >  180.50
|   |   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 36.16
|   |   |   |   |   |   |   |   |--- weights: [6.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- avg_price_per_room >  36.16
|   |   |   |   |   |   |   |   |--- arrival_month <= 11.50
|   |   |   |   |   |   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 2.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  2.00
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 191.00] class: 1
|   |   |   |   |   |   |   |   |--- arrival_month >  11.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 276.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 221.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  221.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [5.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |--- lead_time >  276.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 75.28
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  75.28
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |   |--- weights: [17.00, 0.00] class: 0
|   |   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |   |--- no_of_special_requests <= 2.50
|   |   |   |   |   |   |--- lead_time <= 328.00
|   |   |   |   |   |   |   |--- arrival_month <= 4.50
|   |   |   |   |   |   |   |   |--- lead_time <= 159.50
|   |   |   |   |   |   |   |   |   |--- weights: [8.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- lead_time >  159.50
|   |   |   |   |   |   |   |   |   |--- arrival_year <= 2018.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 96.07
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [8.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  96.07
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- arrival_year >  2018.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 165.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 3
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  165.00
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 18
|   |   |   |   |   |   |   |--- arrival_month >  4.50
|   |   |   |   |   |   |   |   |--- no_of_week_nights <= 9.50
|   |   |   |   |   |   |   |   |   |--- lead_time <= 216.50
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room <= 96.46
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 16
|   |   |   |   |   |   |   |   |   |   |--- avg_price_per_room >  96.46
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 11
|   |   |   |   |   |   |   |   |   |--- lead_time >  216.50
|   |   |   |   |   |   |   |   |   |   |--- lead_time <= 289.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 20
|   |   |   |   |   |   |   |   |   |   |--- lead_time >  289.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 5
|   |   |   |   |   |   |   |   |--- no_of_week_nights >  9.50
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 5.00] class: 1
|   |   |   |   |   |   |--- lead_time >  328.00
|   |   |   |   |   |   |   |--- avg_price_per_room <= 90.08
|   |   |   |   |   |   |   |   |--- weights: [0.00, 10.00] class: 1
|   |   |   |   |   |   |   |--- avg_price_per_room >  90.08
|   |   |   |   |   |   |   |   |--- arrival_month <= 6.00
|   |   |   |   |   |   |   |   |   |--- lead_time <= 341.00
|   |   |   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |   |   |   |--- lead_time >  341.00
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights <= 2.50
|   |   |   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |   |   |--- no_of_week_nights >  2.50
|   |   |   |   |   |   |   |   |   |   |   |--- truncated branch of depth 2
|   |   |   |   |   |   |   |   |--- arrival_month >  6.00
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |--- no_of_special_requests >  2.50
|   |   |   |   |   |   |--- weights: [46.00, 0.00] class: 0
|   |--- avg_price_per_room >  100.04
|   |   |--- no_of_special_requests <= 2.50
|   |   |   |--- arrival_month <= 11.50
|   |   |   |   |--- arrival_month <= 1.50
|   |   |   |   |   |--- no_of_special_requests <= 0.50
|   |   |   |   |   |   |--- weights: [4.00, 0.00] class: 0
|   |   |   |   |   |--- no_of_special_requests >  0.50
|   |   |   |   |   |   |--- lead_time <= 204.50
|   |   |   |   |   |   |   |--- no_of_weekend_nights <= 0.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 2.00] class: 1
|   |   |   |   |   |   |   |--- no_of_weekend_nights >  0.50
|   |   |   |   |   |   |   |   |--- weights: [3.00, 0.00] class: 0
|   |   |   |   |   |   |--- lead_time >  204.50
|   |   |   |   |   |   |   |--- weights: [0.00, 7.00] class: 1
|   |   |   |   |--- arrival_month >  1.50
|   |   |   |   |   |--- weights: [0.00, 2688.00] class: 1
|   |   |   |--- arrival_month >  11.50
|   |   |   |   |--- no_of_special_requests <= 0.50
|   |   |   |   |   |--- weights: [37.00, 0.00] class: 0
|   |   |   |   |--- no_of_special_requests >  0.50
|   |   |   |   |   |--- no_of_special_requests <= 1.50
|   |   |   |   |   |   |--- no_of_week_nights <= 5.50
|   |   |   |   |   |   |   |--- avg_price_per_room <= 145.22
|   |   |   |   |   |   |   |   |--- weights: [0.00, 12.00] class: 1
|   |   |   |   |   |   |   |--- avg_price_per_room >  145.22
|   |   |   |   |   |   |   |   |--- avg_price_per_room <= 147.19
|   |   |   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |   |   |   |--- avg_price_per_room >  147.19
|   |   |   |   |   |   |   |   |   |--- weights: [0.00, 4.00] class: 1
|   |   |   |   |   |   |--- no_of_week_nights >  5.50
|   |   |   |   |   |   |   |--- weights: [1.00, 0.00] class: 0
|   |   |   |   |   |--- no_of_special_requests >  1.50
|   |   |   |   |   |   |--- avg_price_per_room <= 146.39
|   |   |   |   |   |   |   |--- arrival_date <= 28.50
|   |   |   |   |   |   |   |   |--- weights: [7.00, 0.00] class: 0
|   |   |   |   |   |   |   |--- arrival_date >  28.50
|   |   |   |   |   |   |   |   |--- weights: [0.00, 1.00] class: 1
|   |   |   |   |   |   |--- avg_price_per_room >  146.39
|   |   |   |   |   |   |   |--- weights: [0.00, 3.00] class: 1
|   |   |--- no_of_special_requests >  2.50
|   |   |   |--- weights: [142.00, 0.00] class: 0


importance_of_attributes = pd.DataFrame(dTree.feature_importances_, columns = ["Imp"], index = X_train.columns).sort_values(by = 'Imp', ascending = False)
importance_of_attributes


importances = dTree.feature_importances_
indices = np.argsort(importances)

plt.figure(figsize=(12,12))
plt.title('Feature Importances')
plt.barh(range(len(indices)), importances[indices], color='green', align='center')
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel('Relative Importance')
plt.show()


d_Tree = DecisionTreeClassifier(criterion = 'gini',max_depth=3,random_state=1)
d_Tree.fit(X_train, y_train)

DecisionTreeClassifier(max_depth=3, random_state=1)


make_confusion_matrix_for_model(d_Tree, y_test)


# Accuracy on train and test
print("Accuracy value of training set : ",d_Tree.score(X_train, y_train))
print("Accuracy value of test set : ",d_Tree.score(X_test, y_test))

Accuracy value of training set :  0.7710968694426735
Accuracy value of test set :  0.7707664605026228


get_recall_value(d_Tree)

Recall on training set :  0.7480447480447481
Recall on test set :  0.7549019607843137


get_f1_value(d_Tree)

f1 on training set :  0.6889760189659889
f1 on test set :  0.6934031413612565


plt.figure(figsize=(15,10))

tree.plot_tree(d_Tree,feature_names=feature_names,filled=True,fontsize=9,node_ids=True,class_names=True)
plt.show()


#Text Format

print(tree.export_text(d_Tree,feature_names=feature_names,show_weights=True))

|--- lead_time <= 150.50
|   |--- no_of_special_requests <= 0.50
|   |   |--- market_segment_type_Online <= 0.50
|   |   |   |--- weights: [3328.00, 342.00] class: 0
|   |   |--- market_segment_type_Online >  0.50
|   |   |   |--- weights: [3649.00, 3792.00] class: 1
|   |--- no_of_special_requests >  0.50
|   |   |--- no_of_special_requests <= 1.50
|   |   |   |--- weights: [7380.00, 1805.00] class: 0
|   |   |--- no_of_special_requests >  1.50
|   |   |   |--- weights: [4141.00, 269.00] class: 0
|--- lead_time >  150.50
|   |--- avg_price_per_room <= 100.04
|   |   |--- market_segment_type_Online <= 0.50
|   |   |   |--- weights: [434.00, 129.00] class: 0
|   |   |--- market_segment_type_Online >  0.50
|   |   |   |--- weights: [575.00, 1047.00] class: 1
|   |--- avg_price_per_room >  100.04
|   |   |--- no_of_special_requests <= 2.50
|   |   |   |--- weights: [53.00, 2717.00] class: 1
|   |   |--- no_of_special_requests >  2.50
|   |   |   |--- weights: [142.00, 0.00] class: 0


# importance of features of tree building 
importance_of_the_features = pd.DataFrame(d_Tree.feature_importances_, columns = ["Imp"], index = X_train.columns).sort_values(by = 'Imp', ascending = False)
importance_of_the_features


importances_of_d_Tree = d_Tree.feature_importances_
indices = np.argsort(importances_of_d_Tree)

plt.figure(figsize=(10,10))
plt.title('Feature Importances of d_Tree')
plt.barh(range(len(indices)), importances_of_d_Tree[indices], color='violet', align='center')
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel('Relative Importance of d_Tree')
plt.show()


# Choose the type of classifier. 
estimator2 = DecisionTreeClassifier(random_state=1)

# Grid of parameters to choose from
parameters = {'max_depth': np.arange(1,10), 
              'min_samples_leaf': [1, 2, 4, 7, 9, 10, 12],
               "criterion": ["entropy", "gini"],
              'min_impurity_decrease': [0.001,0.01,0.1]
             }

# scoring used to compare parameter
acc_scorer_value = metrics.make_scorer(metrics.recall_score)

#  grid search
grid_obj = GridSearchCV(estimator2, parameters, scoring=acc_scorer_value,cv=5)
grid_obj = grid_obj.fit(X_train, y_train)

# Set the clf to the best combination of parameters
estimator2 = grid_obj.best_estimator_

# Fit the best algorithm to the data. 
estimator2.fit(X_train, y_train)

DecisionTreeClassifier(criterion='entropy', max_depth=3,
                       min_impurity_decrease=0.01, random_state=1)


make_confusion_matrix_for_model(estimator2,y_test)


# Accuracy on train and test
print("Accuracy on training set : ",estimator2.score(X_train, y_train))
print("Accuracy on test set : ",estimator2.score(X_test, y_test))
# Recall on train and test
get_recall_value(estimator2)
get_f1_value(estimator2)

Accuracy on training set :  0.7608630003690904
Accuracy on test set :  0.7609801925937525
Recall on training set :  0.7608157608157609
Recall on test set :  0.7701778385772914
f1 on training set :  0.6832022047384095
f1 on test set :  0.6887552247935569


plt.figure(figsize=(15,10))

tree.plot_tree(estimator2,feature_names=feature_names,filled=True,fontsize=9,node_ids=True,class_names=True)
plt.show()


# Text report showing the rules of a decision tree -

print(tree.export_text(estimator2,feature_names=feature_names,show_weights=True))

|--- lead_time <= 150.50
|   |--- no_of_special_requests <= 0.50
|   |   |--- market_segment_type_Online <= 0.50
|   |   |   |--- weights: [3328.00, 342.00] class: 0
|   |   |--- market_segment_type_Online >  0.50
|   |   |   |--- weights: [3649.00, 3792.00] class: 1
|   |--- no_of_special_requests >  0.50
|   |   |--- no_of_special_requests <= 1.50
|   |   |   |--- weights: [7380.00, 1805.00] class: 0
|   |   |--- no_of_special_requests >  1.50
|   |   |   |--- weights: [4141.00, 269.00] class: 0
|--- lead_time >  150.50
|   |--- avg_price_per_room <= 100.04
|   |   |--- weights: [1009.00, 1176.00] class: 1
|   |--- avg_price_per_room >  100.04
|   |   |--- no_of_special_requests <= 2.50
|   |   |   |--- weights: [53.00, 2717.00] class: 1
|   |   |--- no_of_special_requests >  2.50
|   |   |   |--- weights: [142.00, 0.00] class: 0


importance_estimator2 = (
    pd.DataFrame(
        estimator2.feature_importances_, columns=["Imp"], index=X_train.columns
    ).sort_values(by="Imp", ascending=False)
)
importance_estimator2


importances = estimator2.feature_importances_
indices = np.argsort(importances)

plt.figure(figsize=(12,12))
plt.title('Feature Importances')
plt.barh(range(len(indices)), importances[indices], color='violet', align='center')
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel('Relative Importance')
plt.show()


dtree_tune_train_performance =  model_performance_statsmodel(
    estimator2, X_train, y_train
)
dtree_tune_train_performance


confusion_matrix_for_statsmodel(estimator2, X_train, y_train)


dtree_tune_test_performance =  model_performance_statsmodel(
    estimator2, X_test, y_test
)
dtree_tune_test_performance


confusion_matrix_for_statsmodel(estimator2, X_test, y_test)


dTree_classifier = DecisionTreeClassifier(random_state=1)
path = dTree_classifier.cost_complexity_pruning_path(X_train, y_train)
ccp_alphas, impurities = path.ccp_alphas, path.impurities


pd.DataFrame(path)


fig, bx = plt.subplots(figsize=(10,5))
bx.plot(ccp_alphas[:-1], impurities[:-1], marker='o', drawstyle="steps-post")
bx.set_xlabel("effective alpha")
bx.set_ylabel("total impurity - leaves")
bx.set_title("Total Impurity vs effective alpha for training set")
plt.show()


decision_tree_classifiers = []
for ccp_alpha in ccp_alphas:
    dTree_classifier = DecisionTreeClassifier(random_state=1, ccp_alpha=ccp_alpha)
    dTree_classifier.fit(X_train, y_train)
    decision_tree_classifiers.append(dTree_classifier)
print("Number of nodes in the last tree is: {} with ccp_alpha: {}".format(
      decision_tree_classifiers[-1].tree_.node_count, ccp_alphas[-1]))

Number of nodes in the last tree is: 1 with ccp_alpha: 0.074477957873341


decision_tree_classifiers = decision_tree_classifiers[:-1]
ccp_alphas = ccp_alphas[:-1]

node_counts = [dTree_classifier.tree_.node_count for dTree_classifier in decision_tree_classifiers]
depth = [dTree_classifier.tree_.max_depth for dTree_classifier in decision_tree_classifiers]
fig, bx = plt.subplots(2, 1,figsize=(10,7))
bx[0].plot(ccp_alphas, node_counts, marker='o', drawstyle="steps-post")
bx[0].set_xlabel("alpha")
bx[0].set_ylabel("number of nodes")
bx[0].set_title("Number of nodes vs alpha")
bx[1].plot(ccp_alphas, depth, marker='o', drawstyle="steps-post")
bx[1].set_xlabel("alpha")
bx[1].set_ylabel("depth of the tree")
bx[1].set_title("Depth vs alpha")
fig.tight_layout()


train_score_value = [dTree_classifier.score(X_train, y_train) for dTree_classifier in decision_tree_classifiers]
test_score_value = [dTree_classifier.score(X_test, y_test) for dTree_classifier in decision_tree_classifiers]


fig, cx = plt.subplots(figsize=(10,5))
cx.set_xlabel("alpha")
cx.set_ylabel("accuracy")
cx.set_title("Accuracy vs alpha for training and testing sets")
cx.plot(ccp_alphas, train_score_value, marker='o', label="train",
        drawstyle="steps-post")
cx.plot(ccp_alphas, test_score_value, marker='o', label="test",
        drawstyle="steps-post")
cx.legend()
plt.show()


best_model_head = np.argmax(test_score_value)
best_model = decision_tree_classifiers[best_model_head]
print(best_model)
print('Training accuracy of best model: ',best_model.score(X_train, y_train))
print('Test accuracy of best model: ',best_model.score(X_test, y_test))

DecisionTreeClassifier(ccp_alpha=0.00013438608720037193, random_state=1)
Training accuracy of best model:  0.8453511391470657
Test accuracy of best model:  0.838409144288734


recall_train=[]
for dTree_classifier in decision_tree_classifiers:
    pred_train_set=dTree_classifier.predict(X_train)
    train_values=metrics.recall_score(y_train,pred_train_set)
    recall_train.append(train_values)


recall_test=[]
for dTree_classifier in decision_tree_classifiers:
    pred_test_set=dTree_classifier.predict(X_test)
    test_values=metrics.recall_score(y_test,pred_test_set)
    recall_test.append(test_values)


fig, dx = plt.subplots(figsize=(15,5))
dx.set_xlabel("alpha")
dx.set_ylabel("Recall")
dx.set_title("Recall vs alpha for training and testing sets")
dx.plot(ccp_alphas, recall_train, marker='o', label="train",
        drawstyle="steps-post")
dx.plot(ccp_alphas, recall_test, marker='o', label="test",
        drawstyle="steps-post")
dx.legend()
plt.show()


# creating the model which has highest train and test recall
best_model_1 = np.argmax(recall_test)
best_model_head1 = decision_tree_classifiers[best_model_1]
print(best_model_head1)

DecisionTreeClassifier(ccp_alpha=0.012485002220168545, random_state=1)


make_confusion_matrix_for_model(best_model_head1,y_test)


# Recall of best model on train and test
get_recall_value(best_model_head1)

Recall on training set :  0.7608157608157609
Recall on test set :  0.7701778385772914


get_f1_value(best_model_head1)

f1 on training set :  0.6789169132912232
f1 on test set :  0.68408262454435


plt.figure(figsize=(17,15))

tree.plot_tree(best_model_head1,feature_names=feature_names,filled=True,fontsize=9,node_ids=True,class_names=True)
plt.show()


# Text report 

print(tree.export_text(best_model_head1,feature_names=feature_names,show_weights=True))

|--- lead_time <= 150.50
|   |--- no_of_special_requests <= 0.50
|   |   |--- market_segment_type_Online <= 0.50
|   |   |   |--- weights: [3328.00, 342.00] class: 0
|   |   |--- market_segment_type_Online >  0.50
|   |   |   |--- weights: [3649.00, 3792.00] class: 1
|   |--- no_of_special_requests >  0.50
|   |   |--- weights: [11521.00, 2074.00] class: 0
|--- lead_time >  150.50
|   |--- avg_price_per_room <= 100.04
|   |   |--- weights: [1009.00, 1176.00] class: 1
|   |--- avg_price_per_room >  100.04
|   |   |--- weights: [195.00, 2717.00] class: 1


feature_importance_best_model = pd.DataFrame(best_model_head1.feature_importances_, columns = ["Imp"], index = X_train.columns).sort_values(by = 'Imp', ascending = False)


feature_importance_best_model


importances_best_model = best_model_head1.feature_importances_
indices = np.argsort(importances_best_model)

plt.figure(figsize=(12,12))
plt.title('Feature Importances')
plt.barh(range(len(indices)), importances_best_model[indices], color='violet', align='center')
plt.yticks(range(len(indices)), [feature_names[i] for i in indices])
plt.xlabel('Relative Importance')
plt.show()


comparison_frame_recall = pd.DataFrame({'Model':['Logistic Regression sklearn','Logistic Regression-0.306', 'Logistic Regression - 0.40','Decision Tree stats Model','Decision tree with restricted maximum depth','Decision treee with hyperparameter tuning',
                                         'Decision tree with post-pruning'], 'Train_Recall':[0.61,0.81,0.71,0.76,0.748,0.76,0.76], 'Test_Recall':[0.61,0.81,0.71,0.77,0.745,0.77,0.77]}) 
comparison_frame_recall


comparison_frame_accuracy = pd.DataFrame({'Model':['Logistic Regression sklearn','Logistic Regression-0.306', 'Logistic Regression - 0.40','Decision Tree stats Model','Decision tree with restricted maximum depth','Decision treee with hyperparameter tuning',
                                         'Decision tree with post-pruning'], 'Train_accuracy':[0.79, 0.77,0.79,0.76,0.77, 0.76,0.85 ], 'Test_accuracy':[0.79,0.77,0.79,0.76,0.77,0.76,0.84]}) 
comparison_frame_accuracy


comparison_frame_f1 = pd.DataFrame({'Model':['Logistic Regression sklearn','Logistic Regression-0.306', 'Logistic Regression - 0.40','Decision Tree stats Model','Decision tree with restricted maximum depth','Decision treee with hyperparameter tuning',
                                         'Decision tree with post-pruning'], 'Train_f1':[0.67, 0.71,0.70,0.68,0.69,0.68,0.68 ], 'Test_f1':[0.67, 0.71, 0.70, 0.69,0.69, 0.69, 0.68]}) 
comparison_frame_f1

	count	unique	top	freq	mean	std	min	25%	50%	75%	max
no_of_adults	42576.0	NaN	NaN	NaN	1.916737	0.527524	0.0	2.0	2.0	2.0	4.0
no_of_children	42576.0	NaN	NaN	NaN	0.142146	0.45992	0.0	0.0	0.0	0.0	10.0
no_of_weekend_nights	42576.0	NaN	NaN	NaN	0.89527	0.887864	0.0	0.0	1.0	2.0	8.0
no_of_week_nights	42576.0	NaN	NaN	NaN	2.321167	1.519328	0.0	1.0	2.0	3.0	17.0
type_of_meal_plan	42576	4	Meal Plan 1	31863	NaN	NaN	NaN	NaN	NaN	NaN	NaN
required_car_parking_space	42576.0	NaN	NaN	NaN	0.034362	0.18216	0.0	0.0	0.0	0.0	1.0
room_type_reserved	42576	7	Room_Type 1	29730	NaN	NaN	NaN	NaN	NaN	NaN	NaN
lead_time	42576.0	NaN	NaN	NaN	77.315953	77.279616	0.0	16.0	53.0	118.0	521.0
arrival_year	42576.0	NaN	NaN	NaN	2018.297891	0.626126	2017.0	2018.0	2018.0	2019.0	2019.0
arrival_month	42576.0	NaN	NaN	NaN	6.365488	3.051924	1.0	4.0	6.0	9.0	12.0
arrival_date	42576.0	NaN	NaN	NaN	15.682873	8.813991	1.0	8.0	16.0	23.0	31.0
market_segment_type	42576	5	Online	34169	NaN	NaN	NaN	NaN	NaN	NaN	NaN
repeated_guest	42576.0	NaN	NaN	NaN	0.030886	0.173011	0.0	0.0	0.0	0.0	1.0
no_of_previous_cancellations	42576.0	NaN	NaN	NaN	0.025413	0.358194	0.0	0.0	0.0	0.0	13.0
no_of_previous_bookings_not_canceled	42576.0	NaN	NaN	NaN	0.222731	2.242308	0.0	0.0	0.0	0.0	72.0
avg_price_per_room	42576.0	NaN	NaN	NaN	112.3758	40.865896	0.0	85.5	107.0	135.0	540.0
no_of_special_requests	42576.0	NaN	NaN	NaN	0.768109	0.837264	0.0	0.0	1.0	1.0	5.0
booking_status	42576	2	Not_Canceled	28089	NaN	NaN	NaN	NaN	NaN	NaN	NaN

	count	unique	top	freq	mean	std	min	25%	50%	75%	max
no_of_adults	42576.0	NaN	NaN	NaN	1.916737	0.527524	0.0	2.0	2.0	2.0	4.0
no_of_children	42576.0	NaN	NaN	NaN	0.142146	0.45992	0.0	0.0	0.0	0.0	10.0
no_of_weekend_nights	42576.0	NaN	NaN	NaN	0.89527	0.887864	0.0	0.0	1.0	2.0	8.0
no_of_week_nights	42576.0	NaN	NaN	NaN	2.321167	1.519328	0.0	1.0	2.0	3.0	17.0
type_of_meal_plan	42576	4	Meal Plan 1	31863	NaN	NaN	NaN	NaN	NaN	NaN	NaN
required_car_parking_space	42576.0	NaN	NaN	NaN	0.034362	0.18216	0.0	0.0	0.0	0.0	1.0
room_type_reserved	42576	7	Room_Type 1	29730	NaN	NaN	NaN	NaN	NaN	NaN	NaN
lead_time	42576.0	NaN	NaN	NaN	77.315953	77.279616	0.0	16.0	53.0	118.0	521.0
arrival_year	42576.0	NaN	NaN	NaN	2018.297891	0.626126	2017.0	2018.0	2018.0	2019.0	2019.0
arrival_month	42576.0	NaN	NaN	NaN	6.365488	3.051924	1.0	4.0	6.0	9.0	12.0
arrival_date	42576.0	NaN	NaN	NaN	15.682873	8.813991	1.0	8.0	16.0	23.0	31.0
market_segment_type	42576	5	Online	34169	NaN	NaN	NaN	NaN	NaN	NaN	NaN
repeated_guest	42576.0	NaN	NaN	NaN	0.030886	0.173011	0.0	0.0	0.0	0.0	1.0
no_of_previous_cancellations	42576.0	NaN	NaN	NaN	0.025413	0.358194	0.0	0.0	0.0	0.0	13.0
no_of_previous_bookings_not_canceled	42576.0	NaN	NaN	NaN	0.222731	2.242308	0.0	0.0	0.0	0.0	72.0
avg_price_per_room	42576.0	NaN	NaN	NaN	112.3758	40.865896	0.0	85.5	107.0	135.0	540.0
no_of_special_requests	42576.0	NaN	NaN	NaN	0.768109	0.837264	0.0	0.0	1.0	1.0	5.0
booking_status	42576.0	NaN	NaN	NaN	0.340262	0.473803	0.0	0.0	0.0	1.0	1.0

	count	unique	top	freq	mean	std	min	25%	50%	75%	max
no_of_adults	42576.0	NaN	NaN	NaN	1.916737	0.527524	0.0	2.0	2.0	2.0	4.0
no_of_children	42576.0	NaN	NaN	NaN	0.142146	0.45992	0.0	0.0	0.0	0.0	10.0
no_of_weekend_nights	42576.0	NaN	NaN	NaN	0.89527	0.887864	0.0	0.0	1.0	2.0	8.0
no_of_week_nights	42576.0	NaN	NaN	NaN	2.321167	1.519328	0.0	1.0	2.0	3.0	17.0
type_of_meal_plan	42576	4	Meal Plan 1	31863	NaN	NaN	NaN	NaN	NaN	NaN	NaN
required_car_parking_space	42576.0	NaN	NaN	NaN	0.034362	0.18216	0.0	0.0	0.0	0.0	1.0
room_type_reserved	42576	7	Room_Type 1	29730	NaN	NaN	NaN	NaN	NaN	NaN	NaN
lead_time	42576.0	NaN	NaN	NaN	77.315953	77.279616	0.0	16.0	53.0	118.0	521.0
arrival_year	42576.0	NaN	NaN	NaN	2018.297891	0.626126	2017.0	2018.0	2018.0	2019.0	2019.0
arrival_month	42576.0	NaN	NaN	NaN	6.365488	3.051924	1.0	4.0	6.0	9.0	12.0
arrival_date	42576.0	NaN	NaN	NaN	15.682873	8.813991	1.0	8.0	16.0	23.0	31.0
market_segment_type	42576	5	Online	34169	NaN	NaN	NaN	NaN	NaN	NaN	NaN
repeated_guest	42576.0	NaN	NaN	NaN	0.030886	0.173011	0.0	0.0	0.0	0.0	1.0
no_of_previous_cancellations	42576.0	NaN	NaN	NaN	0.025413	0.358194	0.0	0.0	0.0	0.0	13.0
no_of_previous_bookings_not_canceled	42576.0	NaN	NaN	NaN	0.222731	2.242308	0.0	0.0	0.0	0.0	72.0
avg_price_per_room	42576.0	NaN	NaN	NaN	112.3758	40.865896	0.0	85.5	107.0	135.0	540.0
no_of_special_requests	42576.0	NaN	NaN	NaN	0.768109	0.837264	0.0	0.0	1.0	1.0	5.0
booking_status	42576.0	NaN	NaN	NaN	0.340262	0.473803	0.0	0.0	0.0	1.0	1.0

	no_of_children	no_of_week_nights	required_car_parking_space	lead_time	arrival_year	arrival_month	repeated_guest	no_of_previous_cancellations	avg_price_per_room	no_of_special_requests	type_of_meal_plan_Not Selected	room_type_reserved_Room_Type 4	room_type_reserved_Room_Type 5	room_type_reserved_Room_Type 6	room_type_reserved_Room_Type 7	market_segment_type_Offline	market_segment_type_Online
Odds	1.109639	1.081199	0.220752	1.016761	0.998344	0.964202	0.047508	1.243277	1.016399	0.274469	1.425309	0.882285	0.750884	0.629003	0.498018	0.200443	1.861920
Change_odd%	10.963850	8.119948	-77.924848	1.676082	-0.165559	-3.579829	-95.249228	24.327738	1.639950	-72.553051	42.530875	-11.771462	-24.911557	-37.099658	-50.198167	-79.955668	86.192036

	Logistic Regression sklearn	Logistic Regression-0.307 Threshold	Logistic Regression-0.40 Threshold
Accuracy	0.793410	0.772506	0.788109
Recall	0.613306	0.806752	0.714088
Precision	0.733483	0.627957	0.677914
F1	0.668033	0.706214	0.695531

	no_of_adults	no_of_weekend_nights	no_of_week_nights	type_of_meal_plan	room_type_reserved	lead_time	arrival_year	arrival_month	arrival_date	market_segment_type	avg_price_per_room	no_of_special_requests	booking_status
0	2	1	2	Meal Plan 1	Room_Type 1	224	2017	10	2	Offline	65.00	0	Not_Canceled
1	2	2	3	Not Selected	Room_Type 1	5	2018	11	6	Online	106.68	1	Not_Canceled
2	1	2	1	Meal Plan 1	Room_Type 1	1	2018	2	28	Online	60.00	0	Canceled
3	2	0	2	Meal Plan 1	Room_Type 1	211	2018	5	20	Online	100.00	0	Canceled
4	3	0	3	Not Selected	Room_Type 1	277	2019	7	13	Online	89.10	2	Canceled

	no_of_adults	no_of_children	no_of_weekend_nights	no_of_week_nights	type_of_meal_plan	room_type_reserved	lead_time	arrival_year	arrival_month	arrival_date	market_segment_type	avg_price_per_room	no_of_special_requests	booking_status
18469	2	0	1	3	Meal Plan 1	Room_Type 1	206	2018	8	29	Online	90.95	0	1
28961	2	0	0	4	Meal Plan 1	Room_Type 1	44	2019	6	14	Online	150.00	2	0
10871	2	0	0	1	Meal Plan 1	Room_Type 1	2	2018	7	9	Online	116.27	1	0
6269	2	0	0	1	Not Selected	Room_Type 1	6	2018	9	16	Online	149.00	1	0
47504	2	0	0	3	Meal Plan 1	Room_Type 1	21	2017	9	3	Online	105.00	2	0
48838	2	0	1	1	Meal Plan 1	Room_Type 4	59	2019	3	20	Online	106.20	2	0
49094	2	0	0	2	Meal Plan 1	Room_Type 4	10	2019	2	22	Online	118.00	0	0
8494	2	1	0	1	Meal Plan 1	Room_Type 1	75	2018	10	20	Online	135.00	0	1
41272	2	0	1	3	Not Selected	Room_Type 1	95	2019	5	8	Online	108.00	0	1
29451	2	0	1	2	Not Selected	Room_Type 1	0	2017	8	31	Online	96.33	1	0

	feature	VIF
0	no_of_adults	20.446326
1	no_of_children	2.273281
2	no_of_weekend_nights	2.189851
3	no_of_week_nights	3.759164
4	required_car_parking_space	1.069135
5	lead_time	2.307859
6	arrival_year	247.465491
7	arrival_month	5.601181
8	arrival_date	4.169750
9	repeated_guest	2.074547
10	no_of_previous_cancellations	1.514191
11	no_of_previous_bookings_not_canceled	1.858973
12	avg_price_per_room	19.176685
13	no_of_special_requests	2.054468
14	type_of_meal_plan_Meal Plan 2	1.141328
15	type_of_meal_plan_Meal Plan 3	1.027836
16	type_of_meal_plan_Not Selected	1.588402
17	room_type_reserved_Room_Type 2	1.111350
18	room_type_reserved_Room_Type 3	1.001296
19	room_type_reserved_Room_Type 4	1.823107
20	room_type_reserved_Room_Type 5	1.138882
21	room_type_reserved_Room_Type 6	2.160496
22	room_type_reserved_Room_Type 7	1.173938
23	market_segment_type_Complementary	3.983671
24	market_segment_type_Corporate	11.234312
25	market_segment_type_Offline	31.632538
26	market_segment_type_Online	185.295387

	Logistic Regression sklearn	Logistic Regression-0.306 Threshold	Logistic Regression-0.42 Threshold
Accuracy	0.790730	0.771549	0.791044
Recall	0.610123	0.808254	0.721158
Precision	0.735367	0.630559	0.686266
F1	0.666916	0.708433	0.703280

	Imp
lead_time	0.344685
avg_price_per_room	0.158624
no_of_special_requests	0.097710
arrival_date	0.091935
market_segment_type_Online	0.077835
arrival_month	0.063383
no_of_week_nights	0.054088
no_of_weekend_nights	0.032010
no_of_adults	0.018499
arrival_year	0.016955
type_of_meal_plan_Not Selected	0.009919
room_type_reserved_Room_Type 4	0.008643
required_car_parking_space	0.007496
no_of_children	0.006298
type_of_meal_plan_Meal Plan 2	0.003403
room_type_reserved_Room_Type 5	0.002953
room_type_reserved_Room_Type 2	0.001715
room_type_reserved_Room_Type 6	0.001426
market_segment_type_Corporate	0.000689
market_segment_type_Offline	0.000503
repeated_guest	0.000492
room_type_reserved_Room_Type 7	0.000277
no_of_previous_bookings_not_canceled	0.000185
market_segment_type_Complementary	0.000129
no_of_previous_cancellations	0.000122
room_type_reserved_Room_Type 3	0.000025
type_of_meal_plan_Meal Plan 3	0.000000
const	0.000000

	Imp
lead_time	0.486268
market_segment_type_Online	0.218481
no_of_special_requests	0.209991
avg_price_per_room	0.085260
no_of_weekend_nights	0.000000
type_of_meal_plan_Meal Plan 3	0.000000
market_segment_type_Offline	0.000000
market_segment_type_Corporate	0.000000
market_segment_type_Complementary	0.000000
room_type_reserved_Room_Type 7	0.000000
room_type_reserved_Room_Type 6	0.000000
room_type_reserved_Room_Type 5	0.000000
room_type_reserved_Room_Type 4	0.000000
room_type_reserved_Room_Type 3	0.000000
room_type_reserved_Room_Type 2	0.000000
type_of_meal_plan_Not Selected	0.000000
type_of_meal_plan_Meal Plan 2	0.000000
no_of_week_nights	0.000000
no_of_adults	0.000000
no_of_previous_bookings_not_canceled	0.000000
no_of_previous_cancellations	0.000000
repeated_guest	0.000000
arrival_date	0.000000
arrival_month	0.000000
arrival_year	0.000000
no_of_children	0.000000
required_car_parking_space	0.000000
const	0.000000

	Imp
lead_time	0.434355
no_of_special_requests	0.271789
market_segment_type_Online	0.190693
avg_price_per_room	0.103163
no_of_weekend_nights	0.000000
type_of_meal_plan_Meal Plan 3	0.000000
market_segment_type_Offline	0.000000
market_segment_type_Corporate	0.000000
market_segment_type_Complementary	0.000000
room_type_reserved_Room_Type 7	0.000000
room_type_reserved_Room_Type 6	0.000000
room_type_reserved_Room_Type 5	0.000000
room_type_reserved_Room_Type 4	0.000000
room_type_reserved_Room_Type 3	0.000000
room_type_reserved_Room_Type 2	0.000000
type_of_meal_plan_Not Selected	0.000000
type_of_meal_plan_Meal Plan 2	0.000000
no_of_week_nights	0.000000
no_of_adults	0.000000
no_of_previous_bookings_not_canceled	0.000000
no_of_previous_cancellations	0.000000
repeated_guest	0.000000
arrival_date	0.000000
arrival_month	0.000000
arrival_year	0.000000
no_of_children	0.000000
required_car_parking_space	0.000000
const	0.000000

	ccp_alphas	impurities
0	0.000000	0.003288
1	0.000000	0.003288
2	0.000000	0.003288
3	0.000000	0.003288
4	0.000000	0.003288
...	...	...
2008	0.008721	0.299718
2009	0.012485	0.312203
2010	0.013059	0.325262
2011	0.024185	0.373632
2012	0.074478	0.448110

	Imp
lead_time	0.548006
market_segment_type_Online	0.210444
no_of_special_requests	0.145464
avg_price_per_room	0.096085
no_of_weekend_nights	0.000000
type_of_meal_plan_Meal Plan 3	0.000000
market_segment_type_Offline	0.000000
market_segment_type_Corporate	0.000000
market_segment_type_Complementary	0.000000
room_type_reserved_Room_Type 7	0.000000
room_type_reserved_Room_Type 6	0.000000
room_type_reserved_Room_Type 5	0.000000
room_type_reserved_Room_Type 4	0.000000
room_type_reserved_Room_Type 3	0.000000
room_type_reserved_Room_Type 2	0.000000
type_of_meal_plan_Not Selected	0.000000
type_of_meal_plan_Meal Plan 2	0.000000
no_of_week_nights	0.000000
no_of_adults	0.000000
no_of_previous_bookings_not_canceled	0.000000
no_of_previous_cancellations	0.000000
repeated_guest	0.000000
arrival_date	0.000000
arrival_month	0.000000
arrival_year	0.000000
no_of_children	0.000000
required_car_parking_space	0.000000
const	0.000000

	Model	Train_Recall	Test_Recall
0	Logistic Regression sklearn	0.610	0.610
1	Logistic Regression-0.306	0.810	0.810
2	Logistic Regression - 0.40	0.710	0.710
3	Decision Tree stats Model	0.760	0.770
4	Decision tree with restricted maximum depth	0.748	0.745
5	Decision treee with hyperparameter tuning	0.760	0.770
6	Decision tree with post-pruning	0.760	0.770

	Model	Train_accuracy	Test_accuracy
0	Logistic Regression sklearn	0.79	0.79
1	Logistic Regression-0.306	0.77	0.77
2	Logistic Regression - 0.40	0.79	0.79
3	Decision Tree stats Model	0.76	0.76
4	Decision tree with restricted maximum depth	0.77	0.77
5	Decision treee with hyperparameter tuning	0.76	0.76
6	Decision tree with post-pruning	0.85	0.84

	Model	Train_f1	Test_f1
0	Logistic Regression sklearn	0.67	0.67
1	Logistic Regression-0.306	0.71	0.71
2	Logistic Regression - 0.40	0.70	0.70
3	Decision Tree stats Model	0.68	0.69
4	Decision tree with restricted maximum depth	0.69	0.69
5	Decision treee with hyperparameter tuning	0.68	0.69
6	Decision tree with post-pruning	0.68	0.68

Star Hotels Project¶

Context¶

Objective¶

Data Description¶

Importing necessary libraries and data¶

Data Overview¶

Observations¶

Observations¶

To check if there are any duplicates rows.¶

Observations¶

Observation¶

Verifying for Duplicate Rows.¶

Observations¶

Observations¶

Observation¶

Observations¶

Observations¶

Check for unique values in the column¶

Observation¶

Observation¶

Convert the object variables to Categorical Variables.¶

Observations.¶

Exploratory Data Analysis (EDA)¶

Let us explore numerical variables first¶

Observations on no_of_adults¶

Observations¶

Observations on children¶

Observation¶

Observations on no_of_weekend_nights¶

Observation¶

Observations on required_car_parking_space¶

Observations on lead_time¶

Observations¶

Observations on arrival_month¶

Observations¶

Observations on repeated_guest¶

Observation¶

Observations on no_of_previous_cancellations¶

Observation¶

Observations on no_of_previous_bookings_not_cancelled.¶

Observation¶

Observations¶

Now Lets Explore Categorical Variables.¶

Observation on type_of_meal_plan¶

Observation¶

Observation on room_type_reserved¶

Observation¶

Observation on market_segment_type¶

Observation¶

Observation on Booking_status¶

Observation¶

Bivariate Analysis¶

Plotting Bivariate Analysis to understand the interaction with each other¶

Replace booking_status by numerical values¶

Observation¶

Bivariate Scatter Plots¶

Observations¶

Relationship between type_of_meal_plan and room_type_reserved¶

Observation¶

Relationship betweeen type_of_meal_plan and market_segment_type¶

Observation¶

Relationship between type_of_meal_plan and booking_status¶

Observation¶

Relationship between room_type_reserved and market_segment_type¶

Observations¶

Relationship between market_segment_type and booking_status¶

Observation¶

Relationship between room_type_reserved and booking_status¶

Observation¶

Relationship between no_of_adults and avg_price_per_room¶

Observation¶

Relationship between no_of_children and booking_status¶

Observation¶

Relationship between no_of_weekend_nights and booking_status¶

Observation¶

Relationship between no_of_week_nights and booking_status¶

Observation¶

Relationship between required_car_parking_space and booking_status¶

Observation¶

Relationship between lead_time and booking_status¶